Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

On Linear Representations and Pretraining Data Frequency in Language Models

Jack MerulloNoah A. SmithSarah WiegreffeYanai Elazar
2025
ICLR

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… 

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

Antonis AntoniadesXinyi WangYanai ElazarW. Wang
2025
ICLR

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

Jacob MorrisonClara NaJared FernandezJesse Dodge
2025
ICLR

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… 

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

Bill Yuchen LinYuntian DengK. ChanduYejin Choi
2025
ICLR

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… 

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

Jaehun JungFaeze BrahmanYejin Choi
2025
International Conference on Learning Representations

We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncritically rely on… 

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Jiacheng LiuTaylor BlantonYanai ElazarJesse Dodge
2025
ACL 2025 Demo Track

We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches… 

Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data

Chris KentAdam A. ScaifeN. DunstoneOliver Watt-Meyer
2025
arXiv

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

Kyle RichardsonVivek SrikumarAshish Sabharwal
2025
Proceedings of ICML 2025

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… 

CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation

Peter JansenOyvind TafjordMarissa RadenskyPeter Clark
2025
ACL (Findings)

Despite the surge of interest in autonomous scientific discovery (ASD) of software artifacts (e.g., improved ML algorithms), current ASD systems face two key limitations: (1) they largely explore… 

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

William MerrillAshish Sabharwal
2025
arXiv

Recent theoretical results show transformers cannot express sequential reasoning problems over long input lengths, intuitively because their computational depth is bounded. However, prior work…