Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Holodeck: Language Guided Generation of 3D Embodied AI Environments
3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To miti-gate this limitation,…
Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consuming nature of human…
Social-RAG: Retrieving from Group Interactions to Socially Ground Proactive AI Generation to Group Preferences
AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, but can be unhelpful or even annoying, due to not fitting the group's preferences or…
Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
Multiple-choice question answering (MCQA) is a key competence of performant transformer language models that is tested by mainstream benchmarks. However, recent evidence shows that models can have…
Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of…
LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equations from data…
On Linear Representations and Pretraining Data Frequency in Language Models
Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on…
DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
Automated scientific discovery promises to accelerate progress across scientific domains. However, developing and evaluating an AI agent's capacity for end-to-end scientific reasoning is challenging…
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous studies have…
Paloma: A Benchmark for Evaluating Language Model Fit
Language models (LMs) commonly report perplexity on monolithic data held out from training. Implicitly or explicitly, this data is composed of domains$\unicode{x2013}$varying distributions of…