7 papers
SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models
Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy +3
Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs) can make such inter…
Lessons from the Trenches on Reproducible Evaluation of Language Models
Stella Biderman, Hailey Schoelkopf, Lintang Sutawika +27
Reliable evaluation of language models (LMs) remains an open challenge. Re- searchers and engineers face methodological issues such as the sensitivity of models to evaluation setup…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
TextQuests: How Good are LLMs at Text-Based Video Games?
Long Phan, Mantas Mazeika, Andy Zou +1
Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent ben…
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
Andy Zou, Maxwell Lin, Eliot Jones +14
Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these sys…
Representation Engineering: A Top-Down Approach to AI Transparency
Andy Zou, Long Phan, Sarah Chen +18
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights f…