Bhavana Dalvi Mishra

46 papers A* 10Journal 31Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
MARS: Modular Agent with Reflective Search for Automated AI Research.
CoRR
Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng, Tomas Pfister, Jinsung Yoon
2025 — conf
CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation.
ACL (Findings)
Peter Jansen, Oyvind Tafjord, Marissa Radensky, Pao Siangliulue, Tom Hope, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Daniel S. Weld, Peter Clark
2025 J jnl
CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation.
CoRR
Peter A. Jansen, Oyvind Tafjord, Marissa Radensky, Pao Siangliulue, Tom Hope, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Daniel S. Weld, Peter Clark
2025 A* conf
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models.
ICLR
Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, Peter Clark
2025 A* conf
From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering.
ICLR
Nathaniel Weir, Bhavana Dalvi Mishra, Orion Weller, Oyvind Tafjord, Sam Hornstein, Alexander Sabol, Peter A. Jansen, Benjamin Van Durme, Peter Clark
2025 J jnl
HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation.
CoRR
Rosni Vasu, Peter A. Jansen, Pao Siangliulue, Cristina Sarasua, Abraham Bernstein, Peter Clark, Bhavana Dalvi Mishra
2025 A* conf
HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance.
EMNLP
Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark, Abraham Bernstein
2025 J jnl
HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance.
CoRR
Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark, Abraham Bernstein
2025 A* conf
IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback.
CHI
Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
2025 — conf
Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision.
NAACL (Long Papers)
Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra, Harshit Surana, Julian J. McAuley, Peter Clark, Bodhisattwa Prasad Majumder
2025 J jnl
Latent Factor Models Meets Instructions:Goal-conditioned Latent Factor Discovery without Task Supervision.
CoRR
Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra, Harshit Surana, Julian J. McAuley, Peter Clark, Bodhisattwa Prasad Majumder
2025 J jnl
Open-ended Scientific Discovery via Bayesian Surprise.
CoRR
Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson, Megha Chakravorty, Satvika Reddy Gavireddy, Aditya Parashar, Harshit Surana, Bhavana Dalvi Mishra, Andrew McCallum, Ashish Sabharwal, Peter Clark
2024 J jnl
DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents.
CoRR
Peter A. Jansen, Marc-Alexandre Côté, Tushar Khot, Erin Bransom, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Oyvind Tafjord, Peter Clark
2024 J jnl
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models.
CoRR
Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, Peter Clark
2024 A* conf
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents.
NeurIPS
Peter A. Jansen, Marc-Alexandre Côté, Tushar Khot, Erin Bransom, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Oyvind Tafjord, Peter Clark
2024 A* conf
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic.
EMNLP
Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Jiang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter A. Jansen, Peter Clark, Benjamin Van Durme
2024 J jnl
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic.
CoRR
Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Jiang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter A. Jansen, Peter Clark, Benjamin Van Durme
2024 J jnl
From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answering.
CoRR
Nathaniel Weir, Bhavana Dalvi Mishra, Orion Weller, Oyvind Tafjord, Sam Hornstein, Alexander Sabol, Peter Jansen, Benjamin Van Durme, Peter Clark
2024 J jnl
IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback.
CoRR
Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
2024 A* conf
Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills.
ICML
Kolby Nottingham, Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Sameer Singh, Peter Clark, Roy Fox
2024 J jnl
Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills.
CoRR
Kolby Nottingham, Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Sameer Singh, Peter Clark, Roy Fox
2023 J jnl
BaRDa: A Belief and Reasoning Dataset that Separates Factual Accuracy and Reasoning Ability.
CoRR
Peter Clark, Bhavana Dalvi Mishra, Oyvind Tafjord
2023 J jnl
CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization.
CoRR
Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Peter A. Jansen, Oyvind Tafjord, Niket Tandon, Li Zhang, Chris Callison-Burch, Peter Clark
2023 — conf
Do language models have coherent mental models of everyday things?
ACL (1)
Yuling Gu, Bhavana Dalvi Mishra, Peter Clark
2022 J jnl
Do language models have coherent mental models of everyday things?
CoRR
Yuling Gu, Bhavana Dalvi Mishra, Peter Clark
2022 A* conf
Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning.
EMNLP
Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark
2022 J jnl
Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning.
CoRR
Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark
2022 J jnl
Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE.
CoRR
Yuling Gu, Yao Fu, Valentina Pyatkin, Ian Magnusson, Bhavana Dalvi Mishra, Peter Clark
2022 A* conf
Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement.
EMNLP
Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Clark
2021 J jnl
DREAM: Uncovering Mental Models behind Language Models.
CoRR
Yuling Gu, Bhavana Dalvi Mishra, Peter Clark
2021 J jnl
Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge.
CoRR
Sumithra Bhakthavatsalam, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Peter Clark
2020 J jnl
A Dataset for Tracking Entities in Open Domain Procedural Text.
CoRR
Niket Tandon, Keisuke Sakaguchi, Bhavana Dalvi Mishra, Dheeraj Rajagopal, Peter Clark, Michal Guerquin, Kyle Richardson, Eduard H. Hovy
2020 J jnl
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project.
AI Mag.
Peter Clark, Oren Etzioni, Tushar Khot, Daniel Khashabi, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, Sumithra Bhakthavatsalam, Dirk Groeneveld, Michal Guerquin, Michael Schmitz
2020 — conf
Procedural Reading Comprehension with Attribute-Aware Context Flow.
AKBC
Aida Amini, Antoine Bosselut, Bhavana Dalvi Mishra, Yejin Choi, Hannaneh Hajishirzi
2020 J jnl
Procedural Reading Comprehension with Attribute-Aware Context Flow.
CoRR
Aida Amini, Antoine Bosselut, Bhavana Dalvi Mishra, Yejin Choi, Hannaneh Hajishirzi
2020 J jnl
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language.
CoRR
Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark
2019 — conf
Be Consistent! Improving Procedural Text Comprehension using Label Consistency.
NAACL-HLT (1)
Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie
2019 J jnl
Be Consistent! Improving Procedural Text Comprehension using Label Consistency.
CoRR
Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie
2019 J jnl
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text.
CoRR
Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark
2019 J jnl
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project.
CoRR
Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, Sumithra Bhakthavatsalam, Dirk Groeneveld, Michal Guerquin, Michael Schmitz
2019 J jnl
WIQA: A dataset for "What if..." reasoning over procedural text.
CoRR
Niket Tandon, Bhavana Dalvi Mishra, Keisuke Sakaguchi, Antoine Bosselut, Peter Clark
2018 J jnl
Never-ending learning.
Commun. ACM
Tom M. Mitchell, William W. Cohen, Estevam R. Hruschka Jr., Partha P. Talukdar, Bo Yang, Justin Betteridge, Andrew Carlson, Bhavana Dalvi Mishra, Matt Gardner, Bryan Kisiel, Jayant Krishnamurthy, Ni Lao, Kathryn Mazaitis, Thahir Mohamed, Ndapandula Nakashole, Emmanouil A. Platanios, Alan Ritter, Mehdi Samadi, Burr Settles, Richard C. Wang, Derry Wijaya, Abhinav Gupta, Xinlei Chen, Abulhair Saparov, Malcolm Greaves, Joel Welling
2018 J jnl
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge.
CoRR
Niket Tandon, Bhavana Dalvi Mishra, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter Clark
2018 J jnl
Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension.
CoRR
Bhavana Dalvi Mishra, Lifu Huang, Niket Tandon, Wen-tau Yih, Peter Clark
2017 J jnl
Domain-Targeted, High Precision Knowledge Extraction.
Trans. Assoc. Comput. Linguistics
Bhavana Dalvi Mishra, Niket Tandon, Peter Clark
2015 A* conf
Never-Ending Learning.
AAAI
Tom M. Mitchell, William W. Cohen, Estevam R. Hruschka Jr., Partha Pratim Talukdar, Justin Betteridge, Andrew Carlson, Bhavana Dalvi Mishra, Matthew Gardner, Bryan Kisiel, Jayant Krishnamurthy, Ni Lao, Kathryn Mazaitis, Thahir Mohamed, Ndapandula Nakashole, Emmanouil A. Platanios, Alan Ritter, Mehdi Samadi, Burr Settles, Richard C. Wang, Derry Wijaya, Abhinav Gupta, Xinlei Chen, Abulhair Saparov, Malcolm Greaves, Joel Welling