Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
The Expressive Power of Transformers with Chain of Thought
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…
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
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…
What's In My Big Data?
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…
WildChat: 1M ChatGPT Interaction Logs in the Wild
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…
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
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…
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
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…
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
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…
Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
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…
Tailoring Self-Rationalizers with Multi-Reward Distillation
Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant…
The Generative AI Paradox: "What It Can Create, It May Not Understand"
The recent wave of generative AI has sparked unprecedented global attention, with both excitement and concern over potentially superhuman levels of artificial intelligence: models now take only…