papers

Publications (6)

cs.CR2024

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Danny Halawi, Alexander Wei, Eric Wallace +3

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety…

cs.LG2025

Eliciting Latent Predictions from Transformers with the Tuned Lens

Nora Belrose, Igor Ostrovsky, Lev McKinney +5

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for…

cs.LG2025

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities

Ezra Karger, Houtan Bastani, Chen Yueh-Han +4

Forecasts of future events are essential inputs into informed decision-making. Machine learning (ML) systems have the potential to deliver forecasts at scale, but there is no frame…

cs.AI2024

Dominion: A New Frontier for AI Research

Danny Halawi, Aron Sarmasi, Siena Saltzen +1

In recent years, machine learning approaches have made dramatic advances, reaching superhuman performance in Go, Atari, and poker variants. These games, and others before them, hav…

cs.LG2024

Approaching Human-Level Forecasting with Language Models

Danny Halawi, Fred Zhang, Chen Yueh-Han +1

Forecasting future events is important for policy and decision making. In this work, we study whether language models (LMs) can forecast at the level of competitive human forecaste…

cs.LG2024

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead mod…