Our lab develops cutting-edge, general techniques for developing interactive agents that can speak and act by generating contextually relevant language in grounded environments. Some examples of these tasks include dialog responses, data-to-text, question generation, and text games. Special focuses of our research involve generating text grounded in knowledge and applying reinforcement learning to language. Whether in dialog, technical, or educational domains, grounded text accurately represents facts about the world. Our research focuses on improving the utility of generated text through grounding.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi
ICLR 2024
Project page
PDF
Source code
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Rabeeh Karimi Mahabadi*, Hamish Ivison*, Jaesung Tae, James Henderson, Iz Beltagy, Matthew E. Peters, Arman Cohan
EACL 2024
PDF
Source code
TaskWeb: Selecting Better Source Tasks for Multi-task NLP
Joongwon (Daniel) Kim, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi
EMNLP 2023
Project page
PDF
Source code
Crystal: Introspective Reasoners Reinforced with Self-Feedback
Jiacheng Liu, Ramakanth Pasunuru, Hannaneh Hajishirzi, Yejin Choi, Asli Celikyilmaz
EMNLP 2023
Project page
PDF
Demo
Source code
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Zeqiu Wu*, Yushi Hu*, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, Hannaneh Hajishirzi
NeurIPS 2023
Project page
PDF
Source code
How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
Yizhong Wang*, Hamish Ivison*, Pradeep Dasigi, Jack Hessel, Tushar Khot, Khyathi Raghavi Chandu, David Wadden, Kelsey MacMillan, Noah A. Smith, Iz Beltagy, Hannaneh Hajishirzi
NeurIPS 2023 Datasets and Benchmarks Track
PDF
Source code
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
Rajkumar Ramamurthy*, Prithviraj Ammanabrolu*, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, Yejin Choi
ICLR 2023
Project page
PDF
Source code
INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi
TACL 2023
PDF
Source code
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothee Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, Yuhuai Wu
ICLR 2023
PDF
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
EMNLP 2022
Project page
Dataset
PDF
Demo
Source code
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
Jiacheng Liu, Skyler Hallinan, Ximing Lu, Pengfei He, Sean Welleck, Hannaneh Hajishirzi, Yejin Choi
EMNLP 2022
PDF
Demo
Source code
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Zeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter, Hannaneh Hajishirzi, Mari Ostendorf, Gaurav Singh Tomar
EMNLP 2022
PDF
NaturalProver: Grounded Mathematical Proof Generation with Language Models
Sean Welleck, Jiacheng Liu, Ximing Lu, Hannaneh Hajishirzi, Yejin Choi
NeurIPS 2022
PDF
Source code
Aligning to Social Norms and Values in Interactive Narratives
Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi
NAACL 2022
PDF
Semantic scholar
Situated Dialogue Learning through Procedural Environment Generation
Prithviraj Ammanabrolu, Renee Jia, Mark O. Riedl
ACL 2022
Project page
PDF
Generated Knowledge Prompting for Commonsense Reasoning
Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, Ronan Le Bras, Yejin Choi, Hannaneh Hajishirzi
ACL 2022
PDF
Source code
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
Zeqiu Wu*, Bo-Ru Lu*, Hannaneh Hajishirzi, Mari Ostendorf
EMNLP 2021
PDF
Automatic Document Sketching: Generating Drafts from Analogous Texts
Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Bill Dolan
ACL 2021 Findings
PDF
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Luke Zettlemoyer, Hannaneh Hajishirzi
ACL 2021
PDF
A Controllable Model of Grounded Response Generation
Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, Bill Dolan
AAAI 2021
PDF
Mixture Content Selection for Diverse Sequence Generation
Jaemin Cho, Minjoon Seo, Hannaneh Hajishirzi
EMNLP 2019
PDF
Source code
Text Generation from Knowledge Graphs with Graph Transformers
Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh Hajishirzi
NAACL 2019
PDF
Source code
A Theme-Rewriting Approach for Generating Algebra Word Problems
Rik Koncel-Kedziorski, Ioannis Konstas, Luke Zettlemoyer, Hannaneh Hajishirzi
EMNLP 2016
PDF
Source code