Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 11-20 of 180 papers
Teaching Broad Reasoning Skills via Decomposition-Guided Contexts
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish SabharwalEMNLP • 2022 Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR representations to…Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
Bhavana Dalvi Mishra, Oyvind Tafjord, Peter ClarkEMNLP • 2022 Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a dynamic memory of…What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
Matthew Finlayson, Kyle Richardson, Ashish Sabharwal, Peter ClarkEMNLP • 2022 The instruction learning paradigm—where a model learns to perform new tasks from task descriptions alone—has become popular in general-purpose model research. The capabilities of large transformer models as instruction learners, however, remain poorly under…Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, A. KalyanNeurIPS 2022 • 2022 When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box in the case of deep learning models like large-scale language…One Venue, Two Conferences: The Separation of Chinese and American Citation Networks
Bingchen Zhao, Yuling Gu, Jessica Zosa Forde, Naomi SaphraNeurIPS • AI Cultures Workshop • 2022 At NeurIPS, American and Chinese institutions cite papers from each other’s regions substantially less than they cite endogamously. We build a citation graph to quantify this divide, compare it to European connectivity, and discuss the causes and consequences…Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
Kyle Richardson, Ronen Tamari, Oren Sultan, Reut Tsarfaty, Dafna Shahaf, Ashish SabharwalEMNLP • 2022 Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text encoder and data…Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts
Ben Zhou, Kyle Richardson, Xiaodong Yu, Dan RothEMNLP • 2022 Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite the many datasets…Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE
Yuling Gu, Yao Fu, Valentina Pyatkin, Ian Magnusson, Bhavana Dalvi Mishra, Peter ClarkEMNLP • The Third Workshop on Figurative Language Processing • 2022 Figurative language (e.g., “he flew like the wind”) is challenging to understand, as it is hard to tell what implicit information is being conveyed from the surface form alone. We hypothesize that to perform this task well, the reader needs to mentally…Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking
Ronen Tamari, Kyle Richardson, Aviad Sar-Shalom, Noam Kahlon, Nelson H S Liu, Reut Tsarfaty, Dafna Shahaf SEM • 2022 While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are thus an increasingly important resource for diagnosing model…Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
Niket Tandon, Aman Madaan, Peter Clark, Yiming YangFindings of NAACL • 2022 Large language models (LMs), while power-ful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an LM with (i) a…