Publications

You can also find my articles on my Google Scholar profile.

2026

EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search

Hanane Nour Moussa, Doeun Lee, Sachin Kumar

preprint

BibTeX
@misc{moussa2026elitereplaypreservingdiverse,
  title = {{EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search}},
  author = {Hanane Nour Moussa and Doeun Lee and Sachin Kumar},
  year = {2026},
  note = {Preprint},
  eprint = {2610.22290},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.22290}
}

Tokenization: A Survey for Modern NLP

Marco Cognetta, Christopher Akiki, Pawan Sasanka Ammanamanchi, Catherine Arnett, Thomas Bauwens, Pavel Chizhov, Pieter Delobelle, Konstantin Dobler, Desmond Elliott, Omer Goldman, Tatsuya Hiraoka, Valentin Hofmann, Eugene Jang, Julie Kallini, Ilker Kesen, Sachin Kumar, Sander Land, Jindřich Libovický, Tomasz Limisiewicz, Alisa Liu, Clara Meister, Benjamin Minixhofer, Sangwhan Moon, Tiago Pimentel, David Pohl, Suchir Salhan, Tomohiro Sawada, Pavel Stepachev, Gianluca Vico, Philip Whittington, Xiulin Yang, Yuval Pinter

preprint

BibTeX
@misc{cognetta2026tokenizationasurvey,
  title = {{Tokenization: A Survey for Modern NLP}},
  author = {Marco Cognetta and Christopher Akiki and Pawan Sasanka Ammanamanchi and Catherine Arnett and Thomas Bauwens and Pavel Chizhov and Pieter Delobelle and Konstantin Dobler and Desmond Elliott and Omer Goldman and Tatsuya Hiraoka and Valentin Hofmann and Eugene Jang and Julie Kallini and Ilker Kesen and Sachin Kumar and Sander Land and Jindřich Libovický and Tomasz Limisiewicz and Alisa Liu and Clara Meister and Benjamin Minixhofer and Sangwhan Moon and Tiago Pimentel and David Pohl and Suchir Salhan and Tomohiro Sawada and Pavel Stepachev and Gianluca Vico and Philip Whittington and Xiulin Yang and Yuval Pinter},
  year = {2026},
  note = {Preprint},
  url = {https://www.alphaxiv.org/abs/2609.tokenization-survey-modern-nlp}
}

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models

Emmy Liu, Varun Gangal, Michael Yu, Zhuofu Tao, Karan Singh, Sachin Kumar, Steven Y. Feng

NeurIPS 2026, Evaluations and Datasets Track. To appear

BibTeX
@inproceedings{liu2026halluworldacontrolled,
  title = {{HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models}},
  author = {Emmy Liu and Varun Gangal and Michael Yu and Zhuofu Tao and Karan Singh and Sachin Kumar and Steven Y. Feng},
  year = {2026},
  booktitle = {NeurIPS 2026, Evaluations and Datasets Track},
  eprint = {2605.19341},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.19341}
}

Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties

Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev, Eunjung Yeo, Syed Ishtiaque Ahmed, Nina Markl, Sachin Kumar, Farhan Samir

2026 IEEE Spoken Language Technology (SLT 2026). To Appear

BibTeX
@inproceedings{metzger2026connectingthedots,
  title = {{Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties}},
  author = {Alexander Metzger and Aruna Srivastava and Ruslan Mukhamedvaleev and Eunjung Yeo and Syed Ishtiaque Ahmed and Nina Markl and Sachin Kumar and Farhan Samir},
  year = {2026},
  booktitle = {2026 IEEE Spoken Language Technology (SLT 2026)},
  eprint = {2610.17761},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.17761}
}

One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography

Muge Zhang, Aaron Jencks, Krishna Badikela, Yulia Tsvetkov, Sachin Kumar

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

BibTeX
@inproceedings{2026-emnlp-main-1838,
  title = {{One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography}},
  author = {Zhang, Muge and Jencks, Aaron and Badikela, Krishna and Tsvetkov, Yulia and Kumar, Sachin},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  pages = {41808--41824},
  url = {https://aclanthology.org/2026.emnlp-main.1838/},
  doi = {10.18653/2026.emnlp-main.1838}
}

Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models

Nicholas Sansoterra, Zishuo Zheng, Sachin Kumar

Findings of the Association for Computational Linguistics: EMNLP 2026

BibTeX
@inproceedings{2026-findings-emnlp-1451,
  title = {{Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models}},
  author = {Sansoterra, Nicholas and Zheng, Zishuo and Kumar, Sachin},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  pages = {30912--30927},
  url = {https://aclanthology.org/2026.findings-emnlp.1451/},
  doi = {10.18653/2026.findings-emnlp.1451}
}

The Cost of Sounding Different: Accent Bias in Audio Language Models

Aruna Srivastava, Orevaoghene Ahia, Li Lucy, Ashley Christendat, Sameep Chattopadhyay, Farhan Samir, Tejumade Afonja, Valentin Hofmann, Sachin Kumar, Noah A. Smith, Yulia Tsvetkov

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026). Outstanding Paper Award 🏆

BibTeX
@inproceedings{2026-emnlp-main-1612,
  title = {{The Cost of Sounding Different: Accent Bias in Audio Language Models}},
  author = {Srivastava, Aruna and Ahia, Orevaoghene and Lucy, Li and Christendat, Ashley and Chattopadhyay, Sameep and Samir, Farhan and Afonja, Tejumade and Hofmann, Valentin and Kumar, Sachin and Smith, Noah A. and Tsvetkov, Yulia},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  pages = {36660--36687},
  url = {https://aclanthology.org/2026.emnlp-main.1612/},
  doi = {10.18653/2026.emnlp-main.1612}
}

Dynamic Multi-Byte Prediction With Hierarchical Language Models

Abraham Toluwase Owodunni, Chibuzor Okocha, Christan Grant, Tomasz Limisiewicz, Sachin Kumar

preprint

BibTeX
@misc{owodunni2026dynamicmultibyte,
  title = {{Dynamic Multi-Byte Prediction With Hierarchical Language Models}},
  author = {Abraham Toluwase Owodunni and Chibuzor Okocha and Christan Grant and Tomasz Limisiewicz and Sachin Kumar},
  year = {2026},
  note = {Preprint},
  eprint = {2608.15454},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.15454}
}

Process-Oriented Evaluation of AI-Assisted Scientific Writing

Patrick Queiroz Da Silva, Sanchaita Hazra, Doeun Lee, Sachin Kumar, Bodhisattwa Prasad Majumder

Third Conference on Language Modeling (COLM 2026)

BibTeX
@inproceedings{
silva2026processoriented,
title={Process-Oriented Evaluation of {AI}-Assisted Scientific Writing},
author={Patrick Queiroz Da Silva and Sanchaita Hazra and Doeun Lee and Sachin Kumar and Bodhisattwa Prasad Majumder},
booktitle={Third Conference on Language Modeling},
year={2026},
url={https://openreview.net/forum?id=c6dSFfvY7I}
}

When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering

Doeun Lee, Muge Zhang, Yi Yu, Ashish Manne, Stephen Koesters, Frank Wen, Brady Buchanan, Lynda Villagomez, Oluwatoba Moninuola, James Lim, Kathryn Tobin, Andrew Srisuwananukorn, Ping Zhang, Sachin Kumar

ICML 2026 Workshop on Structured Data for Health (SD4H). Poster

BibTeX
@inproceedings{
lee2026when,
title={When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering},
author={Doeun Lee and Muge Zhang and Yi Yu and Ashish Manne and Stephen Koesters and Frank Wen and Brady Buchanan and Lynda Villagomez and Oluwatoba Moninuola and James Lim and Kathryn Tobin and Andrew Srisuwananukorn and Ping Zhang and Sachin Kumar},
booktitle={ICML 2026 Workshop on Structured Data for Health},
year={2026},
url={https://openreview.net/forum?id=eAx7vA0t99}
}

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining

Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao, Sachin Kumar, Emmy Liu, Steven Y. Feng

preprint

BibTeX
@misc{singh2026tomemorizeor,
  title = {{To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining}},
  author = {Karan Singh and Michael Yu and Varun Gangal and Zhuofu Tao and Sachin Kumar and Emmy Liu and Steven Y. Feng},
  year = {2026},
  note = {Preprint},
  eprint = {2604.00715},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.00715}
}

Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion

Tarun Kathuria, Sachin Kumar

Findings of the Association for Computational Linguistics: ACL 2026

BibTeX
@inproceedings{2026-findings-acl-2117,
  title = {{Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion}},
  author = {Kathuria, Tarun and Kumar, Sachin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  pages = {42625--42643},
  url = {https://aclanthology.org/2026.findings-acl.2117/},
  doi = {10.18653/v1/2026.findings-acl.2117}
}

BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning

Min Jang, Orevaoghene Ahia, Nazif Tamer, Sachin Kumar, Yulia Tsvetkov, Noah A. Smith

preprint

BibTeX
@misc{jang2026bassbenchmarkingaudio,
  title = {{BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning}},
  author = {Min Jang and Orevaoghene Ahia and Nazif Tamer and Sachin Kumar and Yulia Tsvetkov and Noah A. Smith},
  year = {2026},
  note = {Preprint},
  eprint = {2602.04085},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.04085}
}

ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access

Jiwoo Park, Ruoqi Liu, Avani Jagdale, Andrew Srisuwananukorn, Jing Zhao, Lang Li, Ping Zhang, Sachin Kumar

EACL 2026: System Demonstrations

BibTeX
@inproceedings{2026-eacl-demo-26,
  title = {{ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access}},
  author = {Park, Jiwoo and Liu, Ruoqi and Jagdale, Avani and Srisuwananukorn, Andrew and Zhao, Jing and Li, Lang and Zhang, Ping and Kumar, Sachin},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  pages = {359--396},
  url = {https://aclanthology.org/2026.eacl-demo.26/},
  doi = {10.18653/v1/2026.eacl-demo.26}
}

Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing

Sanchaita Hazra*, Doeun Lee*, Bodhisattwa Prasad Majumder, Sachin Kumar

2026 ACM Conference on Intelligent User Interfaces (IUI 2026). *=equal contribution

BibTeX
@inproceedings{hazra2026acceptedwithminor,
  title = {{Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing}},
  author = {Sanchaita Hazra and Doeun Lee and Bodhisattwa Prasad Majumder and Sachin Kumar},
  year = {2026},
  booktitle = {2026 ACM Conference on Intelligent User Interfaces (IUI 2026)},
  eprint = {2511.12529},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.12529}
}

Position: We Need A Unified Definition of Hallucination (It’s The World Model, Stupid!)

Emmy Liu, Varun Prashant Gangal, Chelsea Zou, Michael Yu, Xiaoqi Huang, Alex Chang, Zhuofu Tao, Karanpartap Singh, Sachin Kumar, Steven Y. Feng

International Conference on Machine Learning (ICML 2026), Position Paper Track

BibTeX
@InProceedings{pmlr-v306-liu26gu,
  title = 	 {Position: We Need A Unified Definition of Hallucination ({I}t’s The World Model, Stupid!)},
  author =       {Liu, Emmy and Gangal, Varun Prashant and Zou, Chelsea and Yu, Michael and Huang, Xiaoqi and Chang, Alex and Tao, Zhuofu and Singh, Karanpartap and Kumar, Sachin and Feng, Steven Y.},
  booktitle = 	 {Proceedings of the 43rd International Conference on Machine Learning},
  pages = 	 {171298--171314},
  year = 	 {2026},
  editor = 	 {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto},
  volume = 	 {306},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {06--11 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://raw.githubusercontent.com/mlresearch/v306/main/assets/liu26gu/liu26gu.pdf},
  url = 	 {https://proceedings.mlr.press/v306/liu26gu.html}
}

Reasoning Up the Instruction Ladder for Controllable Language Models

Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar

Findings of the Association for Computational Linguistics: ACL 2026; also presented at Foundations of Reasoning in Language Models (FoRLM) Workshop at NeurIPS 2025

BibTeX
@inproceedings{2026-findings-acl-1960,
  title = {{Reasoning Up the Instruction Ladder for Controllable Language Models}},
  author = {Zheng, Zishuo and Balachandran, Vidhisha and Park, Chan Young and Brahman, Faeze and Kumar, Sachin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  pages = {39332--39354},
  url = {https://aclanthology.org/2026.findings-acl.1960/},
  doi = {10.18653/v1/2026.findings-acl.1960}
}

Continually Adding New Languages to Multilingual Language Models

Abraham Toluwase Owodunni, Sachin Kumar

Transactions on Machine Learning Research (TMLR), 2026; also presented at Multilingual and Equitable Language Technologies (MELT) Workshop @COLM 2025

BibTeX
@article{
owodunni2026continually,
title={Continually Adding New Languages to Multilingual Language Models},
author={Abraham Toluwase Owodunni and Sachin Kumar},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=HE84ER1BNL},
note={}
}

FLEXITOKENS: Flexible Tokenization for Evolving Language Models

Abraham Toluwase Owodunni, Orevaoghene Ahia, Sachin Kumar

Findings of the Association for Computational Linguistics: ACL 2026; also presented at Tokenization Workshop @ICML 2025

BibTeX
@inproceedings{2026-findings-acl-848,
  title = {{FLEXITOKENS: Flexible Tokenization for Evolving Language Models}},
  author = {Owodunni, Abraham Toluwase and Ahia, Orevaoghene and Kumar, Sachin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  pages = {17170--17190},
  url = {https://aclanthology.org/2026.findings-acl.848/},
  doi = {10.18653/v1/2026.findings-acl.848}
}

2025

ScholarEval: Research Idea Evaluation Grounded in Literature

Hanane Nour Moussa*, Patrick Queiroz Da Silva*, Daniel Adu-Ampratwum, Alyson East, Zitong Lu, Nikki Puccetti, Mingyi Xue, Huan Sun, Bodhisattwa Prasad Majumder, Sachin Kumar

preprint. *=equal contribution

BibTeX
@misc{moussa2025scholarevalresearchidea,
  title = {{ScholarEval: Research Idea Evaluation Grounded in Literature}},
  author = {Hanane Nour Moussa and Da Silva, Patrick Queiroz and Daniel Adu-Ampratwum and Alyson East and Zitong Lu and Nikki Puccetti and Mingyi Xue and Huan Sun and Bodhisattwa Prasad Majumder and Sachin Kumar},
  year = {2025},
  note = {Preprint},
  eprint = {2510.16234},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.16234}
}

CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders

Alex Gulko*, Yusen Peng*, Sachin Kumar

BlackboxNLP at EMNLP 2025. *=equal contribution

BibTeX
@inproceedings{gulko2025cebenchtowards,
  title = {{CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders}},
  author = {Alex Gulko and Yusen Peng and Sachin Kumar},
  year = {2025},
  booktitle = {BlackboxNLP at EMNLP 2025},
  eprint = {2509.00691},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.00691}
}

BLAB: Brutally Long Audio Bench

Orevaoghene Ahia, Martijn Bartelds, Kabir Ahuja, Hila Gonen, Valentin Hofmann, Siddhant Arora, Shuyue Stella Li, Vishal Puttagunta, Mofetoluwa Adeyemi, Charishma Buchireddy, Ben Walls, Noah Bennett, Shinji Watanabe, Noah A. Smith, Yulia Tsvetkov, Sachin Kumar

preprint

BibTeX
@misc{ahia2025blabbrutallylong,
  title = {{BLAB: Brutally Long Audio Bench}},
  author = {Orevaoghene Ahia and Martijn Bartelds and Kabir Ahuja and Hila Gonen and Valentin Hofmann and Siddhant Arora and Shuyue Stella Li and Vishal Puttagunta and Mofetoluwa Adeyemi and Charishma Buchireddy and Ben Walls and Noah Bennett and Shinji Watanabe and Noah A. Smith and Yulia Tsvetkov and Sachin Kumar},
  year = {2025},
  note = {Preprint},
  eprint = {2505.03054},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.03054}
}

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Zhouhang Xie, Junda Wu, Yiran Shen, Yu Xia, Xintong Li, Aaron Chang, Ryan Rossi, Sachin Kumar, Bodhisattwa Prasad Majumder, Jingbo Shang, Prithviraj Ammanabrolu, Julian McAuley

Conference on Language Modeling (COLM) 2025

BibTeX
@inproceedings{xie2025asurveyon,
  title = {{A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models}},
  author = {Zhouhang Xie and Junda Wu and Yiran Shen and Yu Xia and Xintong Li and Aaron Chang and Ryan Rossi and Sachin Kumar and Bodhisattwa Prasad Majumder and Jingbo Shang and Prithviraj Ammanabrolu and Julian McAuley},
  year = {2025},
  booktitle = {Conference on Language Modeling (COLM) 2025},
  eprint = {2504.07070},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.07070}
}

On Distributional Robustness of In-Context Learning for Text Classification

Carolina Hatanpää, Noah A. Smith, Sachin Kumar

Second Workshop on Test-Time Adaptation: Putting Updates to the Test! @ICML 2025

BibTeX
@inproceedings{hatanpaa2025ondistributionalrobustness,
  title = {{On Distributional Robustness of In-Context Learning for Text Classification}},
  author = {Carolina Hatanpää and Noah A. Smith and Sachin Kumar},
  year = {2025},
  booktitle = {Second Workshop on Test-Time Adaptation: Putting Updates to the Test! @ICML 2025},
  url = {https://openreview.net/pdf?id=fJgOCX5rDp}
}

Steering off Course: Reliability Challenges in Steering Language Models

Patrick Queiroz Da Silva, Hari Sethuraman, Dheeraj Rajagopal, Hannaneh Hajishirzi, Sachin Kumar

2025 Conference of the Association for Computational Linguistics (ACL 2025). Oral (top 8%), Panel (top 0.8%)

BibTeX
@inproceedings{dasilva2025steeringoffcourse,
  title = {{Steering off Course: Reliability Challenges in Steering Language Models}},
  author = {Da Silva, Patrick Queiroz and Hari Sethuraman and Dheeraj Rajagopal and Hannaneh Hajishirzi and Sachin Kumar},
  year = {2025},
  booktitle = {2025 Conference of the Association for Computational Linguistics (ACL 2025)},
  eprint = {2504.04635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.04635}
}

TESS 2: A Large-Scale Generalist Diffusion Language Model

Jaesung Tae*, Hamish Ivison*, Sachin Kumar, Arman Cohan

ACL 2025. Oral (top 8%). *=equal contribution

BibTeX
@inproceedings{2025-acl-long-1029,
  title = {{TESS 2: A Large-Scale Generalist Diffusion Language Model}},
  author = {Tae, Jaesung and Ivison, Hamish and Kumar, Sachin and Cohan, Arman},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  pages = {21171--21188},
  url = {https://aclanthology.org/2025.acl-long.1029/},
  doi = {10.18653/v1/2025.acl-long.1029}
}

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

Lester James V. Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi

2025 Conference of the Association for Computational Linguistics (ACL 2025)

BibTeX
@inproceedings{miranda2025hybridpreferenceslearning,
  title = {{Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback}},
  author = {Lester James V. Miranda and Yizhong Wang and Yanai Elazar and Sachin Kumar and Valentina Pyatkin and Faeze Brahman and Noah A. Smith and Hannaneh Hajishirzi and Pradeep Dasigi},
  year = {2025},
  booktitle = {2025 Conference of the Association for Computational Linguistics (ACL 2025)},
  eprint = {2410.19133},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.19133}
}

GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models

Harsh Kohli, Sachin Kumar, Huan Sun

2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)

BibTeX
@inproceedings{kohli2025groundcocoaabenchmark,
  title = {{GroundCocoa: A Benchmark for Evaluating Compositional \& Conditional Reasoning in Language Models}},
  author = {Harsh Kohli and Sachin Kumar and Huan Sun},
  year = {2025},
  booktitle = {2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)},
  eprint = {2404.04237},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.04237}
}

ComPO: Community Preferences for Language Model Personalization

Sachin Kumar*, Chan Young Park*, Yulia Tsvetkov, Noah A. Smith, Hannaneh Hajishirzi

2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025). *=equal contribution

BibTeX
@inproceedings{kumar2025compocommunitypreferences,
  title = {{ComPO: Community Preferences for Language Model Personalization}},
  author = {Sachin Kumar and Chan Young Park and Yulia Tsvetkov and Noah A. Smith and Hannaneh Hajishirzi},
  year = {2025},
  booktitle = {2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025)},
  eprint = {2410.16027},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.16027}
}

RewardBench: Evaluating Reward Models for Language Modeling

Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi

2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025) Findings

BibTeX
@inproceedings{lambert2025rewardbenchevaluatingreward,
  title = {{RewardBench: Evaluating Reward Models for Language Modeling}},
  author = {Nathan Lambert and Valentina Pyatkin and Jacob Morrison and LJ Miranda and Bill Yuchen Lin and Khyathi Chandu and Nouha Dziri and Sachin Kumar and Tom Zick and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi},
  year = {2025},
  booktitle = {2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025) Findings},
  eprint = {2403.13787},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.13787}
}

2024

The Art of Saying No: Contextual Noncompliance in Language Models

Faeze Brahman*, Sachin Kumar*, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi

Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024: Datasets and Benchmarks

BibTeX
@inproceedings{brahman2024theartof,
  title = {{The Art of Saying No: Contextual Noncompliance in Language Models}},
  author = {Faeze Brahman and Sachin Kumar and Vidhisha Balachandran and Pradeep Dasigi and Valentina Pyatkin and Abhilasha Ravichander and Sarah Wiegreffe and Nouha Dziri and Khyathi Chandu and Jack Hessel and Yulia Tsvetkov and Noah A. Smith and Yejin Choi and Hannaneh Hajishirzi},
  year = {2024},
  booktitle = {Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024: Datasets and Benchmarks},
  eprint = {2407.12043},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.12043}
}

MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization

Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Valentin Hofmann, Tomasz Limisiewicz, Yulia Tsvetkov, Noah A. Smith

Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024

BibTeX
@inproceedings{ahia2024magnetimprovingthe,
  title = {{MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization}},
  author = {Orevaoghene Ahia and Sachin Kumar and Hila Gonen and Valentin Hofmann and Tomasz Limisiewicz and Yulia Tsvetkov and Noah A. Smith},
  year = {2024},
  booktitle = {Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024},
  eprint = {2407.08818},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.08818}
}

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Liwei Jiang, Kavel Rao, Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, Nouha Dziri

Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024

BibTeX
@inproceedings{jiang2024wildteamingatscale,
  title = {{WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models}},
  author = {Liwei Jiang and Kavel Rao and Seungju Han and Allyson Ettinger and Faeze Brahman and Sachin Kumar and Niloofar Mireshghallah and Ximing Lu and Maarten Sap and Yejin Choi and Nouha Dziri},
  year = {2024},
  booktitle = {Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS) 2024},
  eprint = {2406.18510},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.18510}
}

Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research

Luca Soldaini, Rodney Kinney, Akshita Bhagia, Dustin Schwenk, David Atkinson, Russell Authur, Ben Bogin, Khyathi Chandu, Jennifer Dumas, Yanai Elazar, Valentin Hofmann, Ananya Harsh Jha, Sachin Kumar, Li Lucy, Xinxi Lyu, Nathan Lambert, Ian Magnusson, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Abhilasha Ravichander, Kyle Richardson, Zejiang Shen, Emma Strubell, Nishant Subramani, Oyvind Tafjord, Pete Walsh, Luke Zettlemoyer, Noah A. Smith, Hannaneh Hajishirzi, Iz Beltagy, Dirk Groeneveld, Jesse Dodge, Kyle Lo

2024 Conference of the Association for Computational Linguistics (ACL 2024). Best Resource Paper Award

BibTeX
@inproceedings{soldaini2024dolmaanopen,
  title = {{Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research}},
  author = {Luca Soldaini and Rodney Kinney and Akshita Bhagia and Dustin Schwenk and David Atkinson and Russell Authur and Ben Bogin and Khyathi Chandu and Jennifer Dumas and Yanai Elazar and Valentin Hofmann and Ananya Harsh Jha and Sachin Kumar and Li Lucy and Xinxi Lyu and Nathan Lambert and Ian Magnusson and Jacob Morrison and Niklas Muennighoff and Aakanksha Naik and Crystal Nam and Matthew E. Peters and Abhilasha Ravichander and Kyle Richardson and Zejiang Shen and Emma Strubell and Nishant Subramani and Oyvind Tafjord and Pete Walsh and Luke Zettlemoyer and Noah A. Smith and Hannaneh Hajishirzi and Iz Beltagy and Dirk Groeneveld and Jesse Dodge and Kyle Lo},
  year = {2024},
  booktitle = {2024 Conference of the Association for Computational Linguistics (ACL 2024)},
  eprint = {2402.00159},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.00159}
}

What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization

YuHan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov

2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)

BibTeX
@inproceedings{liu2024whatconstitutesa,
  title = {{What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization}},
  author = {YuHan Liu and Shangbin Feng and Xiaochuang Han and Vidhisha Balachandran and Chan Young Park and Sachin Kumar and Yulia Tsvetkov},
  year = {2024},
  booktitle = {2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)},
  eprint = {2311.09741},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.09741}
}

SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models

Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov, Marjan Ghazvininejad

2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)

BibTeX
@inproceedings{han2024ssd2scaling,
  title = {{SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models}},
  author = {Xiaochuang Han and Sachin Kumar and Yulia Tsvetkov and Marjan Ghazvininejad},
  year = {2024},
  booktitle = {2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)},
  eprint = {2305.14771},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.14771}
}

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

Sachin Kumar, Chan Young Park, Yulia Tsvetkov

International Conference on Learning Representations (ICLR 2024)

BibTeX
@inproceedings{kumar2024genzgenerative,
  title = {{Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions}},
  author = {Sachin Kumar and Chan Young Park and Yulia Tsvetkov},
  year = {2024},
  booktitle = {International Conference on Learning Representations (ICLR 2024)},
  eprint = {2311.07115},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.07115}
}

2023

Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models

Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Jungo Kasai, David R. Mortensen, Noah A. Smith, Yulia Tsvetkov

2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

BibTeX
@inproceedings{ahia2023doalllanguages,
  title = {{Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models}},
  author = {Orevaoghene Ahia and Sachin Kumar and Hila Gonen and Jungo Kasai and David R. Mortensen and Noah A. Smith and Yulia Tsvetkov},
  year = {2023},
  booktitle = {2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)},
  eprint = {2305.13707},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.13707}
}

Minding Language Models’ Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker

Melanie Sclar, Sachin Kumar, Peter West, Alane Suhr, Yejin Choi and Yulia Tsvetkov

2023 Conference of the Association for Computational Linguistics (ACL 2023). Outstanding Paper Award

BibTeX
@inproceedings{sclar2023mindinglanguagemodels,
  title = {{Minding Language Models’ Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker}},
  author = {Melanie Sclar and Sachin Kumar and Peter West and Alane Suhr and Yejin Choi and Yulia Tsvetkov},
  year = {2023},
  booktitle = {2023 Conference of the Association for Computational Linguistics (ACL 2023)},
  eprint = {2306.00924},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.00924}
}

On the Blind Spots of Model-Based Evaluation Metrics for Text Generation

Tianxing He, Jingyu Zhang, Tianle Wang, Sachin Kumar, Kyunghyun Cho, James Glass, Yulia Tsvetkov

2023 Conference of the Association for Computational Linguistics (ACL 2023)

BibTeX
@inproceedings{he2023ontheblind,
  title = {{On the Blind Spots of Model-Based Evaluation Metrics for Text Generation}},
  author = {Tianxing He and Jingyu Zhang and Tianle Wang and Sachin Kumar and Kyunghyun Cho and James Glass and Yulia Tsvetkov},
  year = {2023},
  booktitle = {2023 Conference of the Association for Computational Linguistics (ACL 2023)},
  eprint = {2212.10020},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.10020}
}

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

Xiaochuang Han, Sachin Kumar, Yulia Tsvetkov

2023 Conference of the Association for Computational Linguistics (ACL 2023)

BibTeX
@inproceedings{han2023ssdlmsemi,
  title = {{SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control}},
  author = {Xiaochuang Han and Sachin Kumar and Yulia Tsvetkov},
  year = {2023},
  booktitle = {2023 Conference of the Association for Computational Linguistics (ACL 2023)},
  eprint = {2210.17432},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.17432}
}

Assessing Language Model Deployment with Risk Cards

Leon Derczynski, Hannah Rose Kirk, Vidhisha Balachandran, Sachin Kumar, Yulia Tsvetkov, M. R. Leiser, Saif Mohammad

preprint

BibTeX
@misc{derczynski2023assessinglanguagemodel,
  title = {{Assessing Language Model Deployment with Risk Cards}},
  author = {Leon Derczynski and Hannah Rose Kirk and Vidhisha Balachandran and Sachin Kumar and Yulia Tsvetkov and M. R. Leiser and Saif Mohammad},
  year = {2023},
  note = {Preprint},
  eprint = {2303.18190},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2303.18190}
}

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey

Sachin Kumar*, Vidhisha Balachandran*, Lucille Njoo, Antonios Anastasopoulos, Yulia Tsvetkov

2023 Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023)

BibTeX
@inproceedings{kumar2023languagegenerationmodels,
  title = {{Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey}},
  author = {Sachin Kumar and Vidhisha Balachandran and Lucille Njoo and Antonios Anastasopoulos and Yulia Tsvetkov},
  year = {2023},
  booktitle = {2023 Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023)},
  eprint = {2210.07700},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.07700}
}

2022

Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation

Melanie Sclar, Peter West, Sachin Kumar, Yulia Tsvetkov and Yejin Choi

2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

BibTeX
@inproceedings{sclar2022referencefreesentence,
  title = {{Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation}},
  author = {Melanie Sclar and Peter West and Sachin Kumar and Yulia Tsvetkov and Yejin Choi},
  year = {2022},
  booktitle = {2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)},
  eprint = {2210.13800},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.13800}
}

Gradient-based Constrained Sampling from Language Models

Sachin Kumar, Biswajit Paria, Yulia Tsvetkov

2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

BibTeX
@inproceedings{kumar2022gradientbasedconstrained,
  title = {{Gradient-based Constrained Sampling from Language Models}},
  author = {Sachin Kumar and Biswajit Paria and Yulia Tsvetkov},
  year = {2022},
  booktitle = {2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)},
  eprint = {2205.12558},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.12558}
}

2021

Controlled Text Generation as Continuous Optimization with Multiple Constraints

Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov

Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS) 2021

BibTeX
@inproceedings{kumar2021controlledtextgeneration,
  title = {{Controlled Text Generation as Continuous Optimization with Multiple Constraints}},
  author = {Sachin Kumar and Eric Malmi and Aliaksei Severyn and Yulia Tsvetkov},
  year = {2021},
  booktitle = {Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS) 2021},
  eprint = {2108.01850},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2108.01850}
}

Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs

Monisha Jegadeesan, Sachin Kumar, John Wieting, Yulia Tsvetkov

Multilingual Representation Learning Workshop at EMNLP 2021

BibTeX
@inproceedings{jegadeesan2021improvingthediversity,
  title = {{Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs}},
  author = {Monisha Jegadeesan and Sachin Kumar and John Wieting and Yulia Tsvetkov},
  year = {2021},
  booktitle = {Multilingual Representation Learning Workshop at EMNLP 2021},
  url = {https://aclanthology.org/2021.mrl-1.15/}
}

Machine Translation into Low-Resource Language Varieties

Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, Yulia Tsvetkov

In the proceedings of 2021 Conference on Association of Computational Linguistics (ACL)

BibTeX
@inproceedings{kumar2021machinetranslationinto,
  title = {{Machine Translation into Low-Resource Language Varieties}},
  author = {Sachin Kumar and Antonios Anastasopoulos and Shuly Wintner and Yulia Tsvetkov},
  year = {2021},
  booktitle = {the proceedings of 2021 Conference on Association of Computational Linguistics (ACL)},
  eprint = {2106.06797},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.06797}
}

An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation

Lidia Kidane, Sachin Kumar, Yulia Tsvetkov

The 2nd AfricaNLP Workshop at EACL 2021

BibTeX
@inproceedings{kidane2021anexplorationof,
  title = {{An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation}},
  author = {Lidia Kidane and Sachin Kumar and Yulia Tsvetkov},
  year = {2021},
  booktitle = {The 2nd AfricaNLP Workshop at EACL 2021},
  eprint = {2103.16789},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2103.16789}
}

2020

A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards

Zi-Yi Dou, Sachin Kumar, Yulia Tsvetkov

The 4th Workshop on Neural Generation and Translation (ACL) 2020

BibTeX
@inproceedings{dou2020adeepreinforced,
  title = {{A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards}},
  author = {Zi-Yi Dou and Sachin Kumar and Yulia Tsvetkov},
  year = {2020},
  booktitle = {The 4th Workshop on Neural Generation and Translation (ACL) 2020},
  url = {https://www.aclweb.org/anthology/2020.ngt-1.7.pdf}
}

End-to-End Differentiable GANs for Text Generation

Sachin Kumar, Yulia Tsvetkov

I Can’t Believe It’s Not Better! Workshop at NeurIPS 2020 (PMLR 137)

BibTeX
@InProceedings{pmlr-v137-kumar20a,
  title = 	 {End-to-End Differentiable {GANs} for Text Generation},
  author =       {Kumar, Sachin and Tsvetkov, Yulia},
  booktitle = 	 {Proceedings on "I Can't Believe It's Not Better!" at NeurIPS Workshops},
  pages = 	 {118--128},
  year = 	 {2020},
  editor = 	 {Zosa Forde, Jessica and Ruiz, Francisco and Pradier, Melanie F. and Schein, Aaron},
  volume = 	 {137},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {12 Dec},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v137/kumar20a/kumar20a.pdf},
  url = 	 {https://proceedings.mlr.press/v137/kumar20a.html}
}

2019

A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation

Gayatri Bhat, Sachin Kumar, Yulia Tsvetkov

The 3rd Workshop on Neural Generation and Translation (EMNLP) 2019

BibTeX
@inproceedings{bhat2019amarginbased,
  title = {{A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation}},
  author = {Gayatri Bhat and Sachin Kumar and Yulia Tsvetkov},
  year = {2019},
  booktitle = {The 3rd Workshop on Neural Generation and Translation (EMNLP) 2019},
  url = {https://www.aclweb.org/anthology/D19-5621.pdf}
}

Topics to Avoid: Demoting Latent Confounds in Text Classification

Sachin Kumar, Shuly Wintner, Noah A. Smith, Yulia Tsvetkov

2019 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019

BibTeX
@inproceedings{kumar2019topicstoavoid,
  title = {{Topics to Avoid: Demoting Latent Confounds in Text Classification}},
  author = {Sachin Kumar and Shuly Wintner and Noah A. Smith and Yulia Tsvetkov},
  year = {2019},
  booktitle = {2019 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019},
  eprint = {1909.00453},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1909.00453}
}

Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs

Sachin Kumar & Yulia Tsvetkov

7th International Conference on Learning Representations (ICLR) 2019

BibTeX
@inproceedings{kumar2019vonmisesfisher,
  title = {{Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs}},
  author = {Sachin Kumar and Yulia Tsvetkov},
  year = {2019},
  booktitle = {7th International Conference on Learning Representations (ICLR) 2019},
  url = {https://openreview.net/forum?id=rJlDnoA5Y7}
}

2018

Mining & Summarizing E-petitions for Enhanced Understanding of Public Opinion

Shreshtha Mundra*, Sachin Kumar*, Manjira Sinha, Sandya Mannarswamy

In Proceedings of the International Conference on Information and Knowledge Management (CIKM) 2018

BibTeX
@inproceedings{mundra2018miningsummarizinge,
  title = {{Mining \& Summarizing E-petitions for Enhanced Understanding of Public Opinion}},
  author = {Shreshtha Mundra and Sachin Kumar and Manjira Sinha and Sandya Mannarswamy},
  year = {2018},
  booktitle = {Proceedings of the International Conference on Information and Knowledge Management (CIKM) 2018},
  url = {https://dl.acm.org/citation.cfm?id=3269246}
}

Machine Translation with Continuous Outputs

Sachin Kumar, Yulia Tsvetkov

ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models

BibTeX
@inproceedings{kumar2018machinetranslationwith,
  title = {{Machine Translation with Continuous Outputs}},
  author = {Sachin Kumar and Yulia Tsvetkov},
  year = {2018},
  booktitle = {ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models}
}

2017

Earth Mover Distance Pooling over Siamese LSTMs for Automatic Short Answer Grading

Sachin Kumar, Soumen Chakrabarti, Shourya Roy

In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI) 2017

BibTeX
@inproceedings{kumar2017earthmoverdistance,
  title = {{Earth Mover Distance Pooling over Siamese LSTMs for Automatic Short Answer Grading}},
  author = {Sachin Kumar and Soumen Chakrabarti and Shourya Roy},
  year = {2017},
  booktitle = {Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI) 2017},
  url = {https://www.ijcai.org/proceedings/2017/0284.pdf}
}

2014

Decisions under drift: Adapting binary decision thresholds to drifts in test distribution

Sachin Kumar, Vikas C. Raykar, and Priyanka Agrawal

In Proceedings of the 6th IBM Collaborative Academia Research Exchange Conference. ACM, New York, NY, USA, Article 17, 4 pages. DOI=http://dx.doi.org/10.1145/2662117.2662134

BibTeX
@inproceedings{kumar2014article17,
  title = {{Decisions under drift: Adapting binary decision thresholds to drifts in test distribution}},
  author = {Sachin Kumar and Vikas C. Raykar and Priyanka Agrawal},
  year = {2014},
  booktitle = {Proceedings of the 6th IBM Collaborative Academia Research Exchange Conference},
  url = {http://dx.doi.org/10.1145/2662117.2662134},
  doi = {10.1145/2662117.2662134}
}