Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 21-30 of 1021 papers
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
Sewon Min, Suchin Gururangan, Eric Wallace, Hannaneh Hajishirzi, Noah A. Smith, Luke ZettlemoyerICLR • 2024 The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on low-risk text (e.g., out-of-copyright books or government…The Expressive Power of Transformers with Chain of Thought
William Merrill, Ashish SabharwalICLR • 2024 Recent theoretical work has identified surprisingly simple reasoning problems, such as checking if two nodes in a graph are connected or simulating finite-state machines, that are provably unsolvable by standard transformers that answer immediately after…TRAM: Bridging Trust Regions and Sharpness Aware Minimization
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao PengICLR • 2024 By reducing the curvature of the loss surface in the parameter space, Sharpness-aware minimization (SAM) yields widespread robustness improvement under domain transfer. Instead of focusing on parameters, however, this work considers the transferability of…What's In My Big Data?
Yanai Elazar, Akshita Bhagia, Ian Magnusson, Abhilasha Ravichander, Dustin Schwenk, Alane Suhr, Pete Walsh, Dirk Groeneveld, Luca Soldaini, Sameer Singh, Hanna Hajishirzi, Noah A. Smith, Jesse DodgeICLR • 2024 Large text corpora are the backbone of language models. However, we have a limited understanding of the content of these corpora, including general statistics, quality, social factors, and inclusion of evaluation data (contamination). In this work, we propose…WildChat: 1M ChatGPT Interaction Logs in the Wild
Wenting Zhao, Xiang Ren, J. Hessel, Claire Cardie, Yejin Choi, Yuntian DengICLR • 2024 Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to…WildChat: 1M ChatGPT Interaction Logs in the Wild
Wenting Zhao, Xiang Ren, J. Hessel, Claire Cardie, Yejin Choi, Yuntian DengICLR • 2024 Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to…Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou, Yulia Tsvetkov, Maarten Sap, Reza Shokri, Yejin ChoiICLR • 2024 The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are expected to reason about…Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
Linlu Qiu, Liwei Jiang, Ximing Lu, Melanie Sclar, Valentina Pyatkin, Chandra Bhagavatula, Bailin Wang, Yoon Kim, Yejin Choi, Nouha Dziri, Xiang RenICLR • 2024 The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence. Prior work suggests that language models (LMs) often fall short on…PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, Yejin ChoiICLR • 2024 Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex contextualized situations…Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
Melanie Sclar, Yejin Choi, Yulia Tsvetkov, Alane SuhrICLR • 2024 As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design process is…