Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
A Design Space for Intelligent and Interactive Writing Assistants
In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge…
Improving Language Models with Advantage-based Offline Policy Gradients
Language Models (LMs) achieve substantial language capabilities when finetuned using Reinforcement Learning with Human Feedback (RLHF). However, RLHF is an unstable and data-hungry process that…
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…
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…
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…
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Recent works have showcased the ability of LLMs to embody diverse personas in their responses, exemplified by prompts like 'You are Yoda. Explain the Theory of Relativity.' While this ability allows…
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate.…
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts…
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
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…
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is…