Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
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…
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of…
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…
Holistically Evaluating the Environmental Impact of Creating Language Models
As the performance of artificial intelligence systems has dramatically increased, so too has the environmental impact of creating these systems. While many model developers release estimates of the…
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…
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024 tasks carefully…
Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data
Machine learning weather models trained on observed atmospheric conditions can outperform conventional physics-based models at short- to medium-range (1-14 day) forecast timescales. Here we take the…
Understanding the Logic of Direct Preference Alignment through Logic
Recent direct preference alignment algorithms (DPA), such as DPO, have shown great promise in aligning large language models to human preferences. While this has motivated the development of many…