Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 341-350 of 991 papers
CiteRead: Integrating Localized Citation Contexts into Scientific Paper Reading
Napol Rachatasumrit, Jonathan Bragg, Amy X. Zhang, Daniel S. WeldIUI • 2022 When reading a scholarly paper, scientists oftentimes wish to understand how follow-on work has built on or engages with what they are reading. While a paper itself can only discuss prior work, some scientific search engines can provide a list of all…Probing Factually Grounded Content Transfer with Factual Ablation
Peter West, Chris Quirk, Michel Galley, Yejin ChoiFindings of ACL • 2022 Despite recent success, large neural models often generate factually incorrect text. Compounding this is the lack of a standard automatic evaluation for factuality–it cannot be meaningfully improved if it cannot be measured. Grounded generation promises a…Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search
Daniel King, Zejiang Shen, Nishant Subramani, Daniel S. Weld, Iz Beltagy, Doug DowneyGEM Workshop 2022 • 2022 Abstractive summarization systems today produce fluent and relevant output, but often “hallucinate” statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that models hallucinate…Memory-assisted prompt editing to improve GPT-3 after deployment
Aman Madaan, Niket Tandon, Peter Clark, Yiming YangACL • Workshop on Commonsense Reasoning • 2022 Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homonym, while the user intended a synonym. Our goal is to effectively correct…Object Manipulation via Visual Target Localization
Kiana Ehsani, Ali Farhadi, Aniruddha Kembhavi, Roozbeh MottaghiarXiv • 2022 Object manipulation is a critical skill required for Embodied AI agents interacting with the world around them. Training agents to manipulate objects, poses many challenges. These include occlusion of the target object by the agent’s arm, noisy object…ScienceWorld: Is your Agent Smarter than a 5th Grader?
Ruoyao Wang, Peter Alexander Jansen, Marc-Alexandre Côté, Prithviraj AmmanabroluarXiv • 2022 This paper presents a new benchmark, SCIENCEWORLD, to test agents’ scientific reasoning abilities in a new interactive text environment at the level of a standard elementary school science curriculum. Despite the recent transformer-based progress seen in…Staged Training for Transformer Language Models
Sheng Shen, Pete Walsh, K. Keutzer, Jesse Dodge, Matthew E. Peters, Iz BeltagyICML 2022 • 2022 The current standard approach to scaling transformer language models trains each model size from a different random initialization. As an alternative, we consider a staged training setup that begins with a small model and incremen-tally increases the amount…Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
Kung-Hsiang Huang, Preslav Nakov, Yejin Choi, Heng JiarXiv • 2022 While there has been a lot of research and many recent advances in neural fake news detection, defending against human-written disinformation remains underexplored. Upon analyzing current approaches for fake news generation and human-crafted articles, we…LIMEADE: From AI Explanations to Advice Taking
B. Lee, Doug Downey, Kyle Lo, Daniel S. WeldTiiS • 2022 Research in human-centered AI has shown the benefits of systems that can explain their predictions. Methods that allow an AI to take advice from humans in response to explanations are similarly useful. While both capabilities are well-developed for…Text-based NP Enrichment
Yanai Elazar, Victoria Basmov, Yoav Goldberg, Reut TsarfatyTACL • 2022 Understanding the relations between entities denoted by NPs in text is a critical part of human-like natural language understanding. However, only a fraction of such relations is covered by NLP tasks and models nowadays. In this work, we establish the task of…