Swarnadeep Saha

50 papers A* 9A 1B 1Journal 25Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Reasoning over mathematical objects: on-policy reward modeling and test time aggregation. CoRR Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, Ilia Kulikov, Jack Lanchantin, Xian Li, Tianjian Li, Bo Liu, Graham Neubig, Anaelia Ovalle, Swarnadeep Saha, Sainbayar Sukhbaatar, Sean Welleck, Jason Weston, Chenxi Whitehouse, Adina Williams, Jing Xu, Ping Yu, Weizhe Yuan, Jingyu Zhang, Wenting Zhao
2026	J	`jnl`	Text-to-Stage: Spatial Layouts from Long-form Narratives. CoRR Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse, Sanjeel Parekh, Calvin Murdock, Yuliang Li, W. Owen Brimijoin, Vamsi Krishna Ithapu, Ishwarya Ananthabhotla
2025	J	`jnl`	Bridging Offline and Online Reinforcement Learning for LLMs. CoRR Jack Lanchantin, Angelica Chen, Janice Lan, Xian Li, Swarnadeep Saha, Tianlu Wang, Jing Xu, Ping Yu, Weizhe Yuan, Jason E. Weston, Sainbayar Sukhbaatar, Ilia Kulikov
2025	J	`jnl`	Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense. CoRR Leitian Tao, Ilia Kulikov, Swarnadeep Saha, Tianlu Wang, Jing Xu, Sharon Li, Jason E. Weston, Ping Yu
2025	J	`jnl`	J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning. CoRR Chenxi Whitehouse, Tianlu Wang, Ping Yu, Xian Li, Jason Weston, Ilia Kulikov, Swarnadeep Saha
2025	J	`jnl`	Jointly Reinforcing Diversity and Quality in Language Model Generations. CoRR Tianjian Li, Yiming Zhang, Ping Yu, Swarnadeep Saha, Daniel Khashabi, Jason Weston, Jack Lanchantin, Tianlu Wang
2025	A*	`conf`	Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge. ICML Swarnadeep Saha, Xian Li, Marjan Ghazvininejad, Jason E. Weston, Tianlu Wang
2025	J	`jnl`	Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge. CoRR Swarnadeep Saha, Xian Li, Marjan Ghazvininejad, Jason Weston, Tianlu Wang
2025	A*	`conf`	MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning. EMNLP Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2025	J	`jnl`	OptimalThinkingBench: Evaluating Over and Underthinking in LLMs. CoRR Pranjal Aggarwal, Seungone Kim, Jack Lanchantin, Sean Welleck, Jason Weston, Ilia Kulikov, Swarnadeep Saha
2025	A*	`conf`	System 1.x: Learning to Balance Fast and Slow Planning with Language Models. ICLR Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal
2025	J	`jnl`	The Majority is not always right: RL training for solution aggregation. CoRR Wenting Zhao, Pranjal Aggarwal, Swarnadeep Saha, Asli Celikyilmaz, Jason Weston, Ilia Kulikov
2024	—	`conf`	Branch-Solve-Merge Improves Large Language Model Evaluation and Generation. NAACL-HLT Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li
2024	—	`—`	Interpretable, Modular, and Structured Multi-step Reasoning over Natural Language. Swarnadeep Saha
2024	A*	`conf`	MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models. ICML Justin Chih-Yao Chen, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2024	J	`jnl`	MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models. CoRR Justin Chih-Yao Chen, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2024	J	`jnl`	MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning. CoRR Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2024	—	`conf`	ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs. ACL (1) Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal
2024	J	`jnl`	System-1.x: Learning to Balance Fast and Slow Planning with Language Models. CoRR Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal
2023	J	`jnl`	Branch-Solve-Merge Improves Large Language Model Evaluation and Generation. CoRR Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li
2023	J	`jnl`	Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Theory of Mind. CoRR Swarnadeep Saha, Peter Hase, Mohit Bansal
2023	A*	`conf`	Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization. NeurIPS Swarnadeep Saha, Peter Hase, Mohit Bansal
2023	—	`conf`	MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation. ACL (Findings) Swarnadeep Saha, Xinyan Yu, Mohit Bansal, Ramakanth Pasunuru, Asli Celikyilmaz
2023	A*	`conf`	ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness. EMNLP Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal
2023	J	`jnl`	ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness. CoRR Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal
2023	J	`jnl`	ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs. CoRR Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal
2023	A*	`conf`	Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees. ICLR Swarnadeep Saha, Shiyue Zhang, Peter Hase, Mohit Bansal
2022	A*	`conf`	Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations. EMNLP Swarnadeep Saha, Peter Hase, Nazneen Rajani, Mohit Bansal
2022	J	`jnl`	Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations. CoRR Swarnadeep Saha, Peter Hase, Nazneen Rajani, Mohit Bansal
2022	—	`conf`	Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning. ACL (1) Swarnadeep Saha, Prateek Yadav, Mohit Bansal
2022	J	`jnl`	Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning. CoRR Swarnadeep Saha, Prateek Yadav, Mohit Bansal
2022	J	`jnl`	MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation. CoRR Swarnadeep Saha, Xinyan Velocity Yu, Mohit Bansal, Ramakanth Pasunuru, Asli Celikyilmaz
2022	J	`jnl`	Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees. CoRR Swarnadeep Saha, Shiyue Zhang, Peter Hase, Mohit Bansal
2021	—	`conf`	ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning. EMNLP (1) Swarnadeep Saha, Prateek Yadav, Lisa Bauer, Mohit Bansal
2021	J	`jnl`	ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning. CoRR Swarnadeep Saha, Prateek Yadav, Lisa Bauer, Mohit Bansal
2021	—	`conf`	multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning. NAACL-HLT Swarnadeep Saha, Prateek Yadav, Mohit Bansal
2021	J	`jnl`	multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning. CoRR Swarnadeep Saha, Prateek Yadav, Mohit Bansal
2020	—	`conf`	ConjNLI: Natural Language Inference Over Conjunctive Sentences. EMNLP (1) Swarnadeep Saha, Yixin Nie, Mohit Bansal
2020	J	`jnl`	ConjNLI: Natural Language Inference Over Conjunctive Sentences. CoRR Swarnadeep Saha, Yixin Nie, Mohit Bansal
2020	—	`conf`	PRover: Proof Generation for Interpretable Reasoning over Rules. EMNLP (1) Swarnadeep Saha, Sayan Ghosh, Shashank Srivastava, Mohit Bansal
2020	J	`jnl`	PRover: Proof Generation for Interpretable Reasoning over Rules. CoRR Swarnadeep Saha, Sayan Ghosh, Shashank Srivastava, Mohit Bansal
2019	A*	`conf`	Aligning Learning Outcomes to Learning Resources: A Lexico-Semantic Spatial Approach. IJCAI Swarnadeep Saha, Malolan Chetlur, Tejas Indulal Dhamecha, K. Gayathri Wijayarathna, Red Mendoza, Paul Gagnon, Nabil Zary, Shantanu Godbole
2019	J	`jnl`	Joint Multi-Domain Learning for Automatic Short Answer Grading. CoRR Swarnadeep Saha, Tejas I. Dhamecha, Smit Marvaniya, Peter W. Foltz, Renuka Sindhgatta, Bikram Sengupta
2019	—	`conf`	Learning Outcomes and Their Relatedness in a Medical Curriculum. BEA@ACL Sneha Mondal, Tejas I. Dhamecha, Shantanu Godbole, Smriti Pathak, Red Mendoza, K. Gayathri Wijayarathna, Nabil Zary, Swarnadeep Saha, Malolan Chetlur
2019	—	`conf`	Pre-Training BERT on Domain Resources for Short Answer Grading. EMNLP/IJCNLP (1) Chul Sung, Tejas I. Dhamecha, Swarnadeep Saha, Tengfei Ma, Vinay Reddy, Rishi Arora
2018	—	`conf`	Balancing Human Efforts and Performance of Student Response Analyzer in Dialog-Based Tutors. AIED (1) Tejas I. Dhamecha, Smit Marvaniya, Swarnadeep Saha, Renuka Sindhgatta, Bikram Sengupta
2018	A	`conf`	Creating Scoring Rubric from Representative Student Answers for Improved Short Answer Grading. CIKM Smit Marvaniya, Swarnadeep Saha, Tejas I. Dhamecha, Peter W. Foltz, Renuka Sindhgatta, Bikram Sengupta
2018	B	`conf`	Open Information Extraction from Conjunctive Sentences. COLING Swarnadeep Saha, Mausam
2018	—	`conf`	Sentence Level or Token Level Features for Automatic Short Answer Grading?: Use Both. AIED (1) Swarnadeep Saha, Tejas I. Dhamecha, Smit Marvaniya, Renuka Sindhgatta, Bikram Sengupta
2017	—	`conf`	Bootstrapping for Numerical Open IE. ACL (2) Swarnadeep Saha, Harinder Pal, Mausam