Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 51-60 of 221 papers
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
Maarten Sap, Ronan Lebras, Daniel Fried, Yejin ChoiEMNLP • 2022 Social intelligence and Theory of Mind (T O M), i.e., the ability to reason about the different mental states, intents, and reactions of all people involved, allow humans to effectively navigate and understand everyday social interactions. As NLP systems are…The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning
Jack Hessel, Jena D. Hwang, Jae Sung Park, Rowan Zellers, Chandra Bhagavatula, Anna Rohrbach, Kate Saenko, Yejin ChoiECCV • 2022 Humans have remarkable capacity to reason abductively and hypothesize about what lies beyond the literal content of an image. By identifying concrete visual clues scattered throughout a scene, we almost can’t help but draw probable inferences beyond the…NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation
Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha SwayamdiptaConference on Empirical Methods in Natural Language Processing • 2022 While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing approaches for…Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
Jiacheng Liu, Skyler Hallinan, Ximing Lu, Pengfei He, S. Welleck, Hannaneh Hajishirzi, Yejin ChoiConference on Empirical Methods in Natural Language Processing • 2022 Knowledge underpins reasoning. Recent research demonstrates that when relevant knowledge is provided as additional context to commonsense question answering (QA), it can substantially enhance the performance even on top of state-of-the-art. The fundamental…REV: Information-Theoretic Evaluation of Free-Text Rationales
Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha SwayamdiptaarXiv • 2022 information. Future work might explore evaluation that penalizes rationales which support incorrect predictions, thus bridging together predictive performance with interpretability metrics.Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
R. Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, R. Sifa, C. Bauckhage, Hannaneh Hajishirzi, Yejin ChoiArXiv • 2022 We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, using RL…Aligning to Social Norms and Values in Interactive Narratives
Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin ChoiNAACL • 2022 We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games—environments wherein an agent perceives and interacts with a world through natural language. Such interactive agents are…Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
Maarten Sap, Swabha Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, Noah A. SmithNAACL • 2022 Warning : this paper discusses and contains content that is offensive or upsetting. The perceived toxicity of language can vary based on someone’s identity and beliefs, but this variation is often ignored when collecting toxic language datasets, resulting in…Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand
Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Lavinia Dunagan, Jacob Morrison, Alexander R. Fabbri, Yejin Choi, Noah A. SmithNAACL • 2022 Natural language processing researchers have identified limitations of evaluation methodology for generation tasks, with new questions raised about the validity of automatic metrics and of crowdworker judgments. Meanwhile, efforts to improve generation models…Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer
Yanpeng Zhao, Jack Hessel, Youngjae Yu, Ximing Lu, Rowan Zellers, Yejin ChoiNAACL • 2022 Machines that can represent and describe environmental soundscapes have practical poten-tial, e.g., for audio tagging and captioning. Pre-vailing learning paradigms of audio-text connections have been relying on parallel audio-text data, which is, however…