6 citations · 14 across the 11 of their papers we have counts for
13 papers
Understanding and Reducing Misalignment in Persuasion Optimization
Boyi Wei, Ruta Desai, Peter Henderson +1
Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training models to be persuasive. But wha…
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
Hadas Orgad, Boyi Wei, Kaden Zheng +4
Large language models remain vulnerable to jailbreaks that elicit harmful responses, yet the mechanism behind harmful response generation is poorly understood. Here, we investigate…
Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
Boyi Wei, Zora Che, Nathaniel Li +10
Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad acto…
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
Sayash Kapoor, Benedikt Stroebl, Peter Kirgis +28
AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of…
Scaling Latent Reasoning via Looped Language Models
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training…
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
Shuai Shao, Qihan Ren, Chen Qian +8
Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the environment, demonstrating strong c…
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Boyi Wei, Benedikt Stroebl, Jiacen Xu +3
Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier…
On Evaluating the Durability of Safeguards for Open-Weight LLMs
Xiangyu Qi, Boyi Wei, Nicholas Carlini +7
Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical sa…
An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Łucki, Boyi Wei, Yangsibo Huang +3
Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazard…
Evaluating Copyright Takedown Methods for Language Models
Boyi Wei, Weijia Shi, Yangsibo Huang +5
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content…
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Tinghao Xie, Xiangyu Qi, Yi Zeng +13
Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…