Makesh Narsimhan Sreedhar

28 papers A* 2Journal 16Unranked 10
YearRankTypeTitle / Venue / Authors
2025 — conf
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails.
NAACL (Long Papers)
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, Christopher Parisien
2025 J jnl
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails.
CoRR
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, Christopher Parisien
2025 — conf
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications.
ACL (5)
Traian Rebedea, Leon Derczynski, Shaona Ghosh, Makesh Narsimhan Sreedhar, Faeze Brahman, Liwei Jiang, Bo Li, Yulia Tsvetkov, Christopher Parisien, Yejin Choi
2025 J jnl
Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies.
CoRR
Prasoon Varshney, Makesh Narsimhan Sreedhar, Liwei Jiang, Traian Rebedea, Christopher Parisien
2025 — conf
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models.
EMNLP (Findings)
Makesh Narsimhan Sreedhar, Traian Rebedea, Christopher Parisien
2025 J jnl
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models.
CoRR
Makesh Narsimhan Sreedhar, Traian Rebedea, Christopher Parisien
2025 J jnl
Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training.
CoRR
Mingjie Liu, Shizhe Diao, Jian Hu, Ximing Lu, Xin Dong, Hao Zhang, Alexander Bukharin, Shaokun Zhang, Jiaqi Zeng, Makesh Narsimhan Sreedhar, Gerald Shen, David Mosallanezhad, Di Zhang, Jonas Yang, June Yang, Oleksii Kuchaiev, Guilin Liu, Zhiding Yu, Pavlo Molchanov, Yejin Choi, Jan Kautz, Yi Dong
2024 — conf
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues.
EMNLP (Findings)
Makesh Narsimhan Sreedhar, Traian Rebedea, Shaona Ghosh, Jiaqi Zeng, Christopher Parisien
2024 J jnl
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues.
CoRR
Makesh Narsimhan Sreedhar, Traian Rebedea, Shaona Ghosh, Christopher Parisien
2024 A* conf
HelpSteer 2: Open-source dataset for training top-performing reward models.
NeurIPS
Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy Zhang, Makesh Narsimhan Sreedhar, Oleksii Kuchaiev
2024 J jnl
HelpSteer2: Open-source dataset for training top-performing reward models.
CoRR
Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy J. Zhang, Makesh Narsimhan Sreedhar, Oleksii Kuchaiev
2024 — conf
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM.
NAACL-HLT
Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Polak Scowcroft, Neel Kant, Aidan Swope, Oleksii Kuchaiev
2024 A* conf
Unsupervised Extraction of Dialogue Policies from Conversations.
EMNLP
Makesh Narsimhan Sreedhar, Traian Rebedea, Christopher Parisien
2024 J jnl
Unsupervised Extraction of Dialogue Policies from Conversations.
CoRR
Makesh Narsimhan Sreedhar, Traian Rebedea, Christopher Parisien
2023 J jnl
Evolving Domain Adaptation of Pretrained Language Models for Text Classification.
CoRR
Yun-Shiuan Chuang, Yi Wu, Dhruv Gupta, Rheeya Uppaal, Ananya Kumar, Luhang Sun, Makesh Narsimhan Sreedhar, Sijia Yang, Timothy T. Rogers, Junjie Hu
2023 J jnl
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM.
CoRR
Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Polak Scowcroft, Neel Kant, Aidan Swope, Oleksii Kuchaiev
2023 — conf
Local Byte Fusion for Neural Machine Translation.
ACL (1)
Makesh Narsimhan Sreedhar, Xiangpeng Wan, Yu Cheng, Junjie Hu
2023 — conf
NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails.
EMNLP (Demos)
Traian Rebedea, Razvan Dinu, Makesh Narsimhan Sreedhar, Christopher Parisien, Jonathan Cohen
2023 J jnl
NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails.
CoRR
Traian Rebedea, Razvan Dinu, Makesh Narsimhan Sreedhar, Christopher Parisien, Jonathan Cohen
2023 — conf
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA.
ACL (1)
Gowtham Ramesh, Makesh Narsimhan Sreedhar, Junjie Hu
2023 J jnl
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA.
CoRR
Gowtham Ramesh, Makesh Narsimhan Sreedhar, Junjie Hu
2023 — conf
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF.
EMNLP (Findings)
Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev
2023 J jnl
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF.
CoRR
Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev
2022 J jnl
Local Byte Fusion for Neural Machine Translation.
CoRR
Makesh Narsimhan Sreedhar, Xiangpeng Wan, Yu Cheng, Junjie Hu
2022 J jnl
Prompt Learning for Domain Adaptation in Task-Oriented Dialogue.
CoRR
Makesh Narsimhan Sreedhar, Christopher Parisien
2020 J jnl
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback.
CoRR
Makesh Narsimhan Sreedhar, Kun Ni, Siva Reddy
2020 J jnl
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation.
CoRR
Victor Schmidt, Makesh Narsimhan Sreedhar, Mostafa ElAraby, Irina Rish
2020 — conf
You could have said that instead: Improving Chatbots with Natural Language Feedback.
EMNLP (Findings)
Makesh Narsimhan Sreedhar, Kun Ni, Siva Reddy