7 papers
HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
Xuhui Zhou, Hyunwoo Kim, Faeze Brahman +9
AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examini…
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson +4
We investigate the logical reasoning capabilities of large language models (LLMs) and their scalability in complex non-monotonic reasoning. To this end, we introduce ZebraLogic, a…
CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming
Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin +8
Robust, diverse, and challenging cultural knowledge benchmarks are essential for measuring our progress towards making LMs that are helpful across diverse cultures. We introduce Cu…
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Zhangchen Xu, Fengqing Jiang, Luyao Niu +2
Instruction tuning has been widely adopted to ensure large language models (LLMs) follow user instructions effectively. The resulting instruction-following capabilities of LLMs hea…
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
Fengqing Jiang, Zhangchen Xu, Luyao Niu +2
Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fi…
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Seungju Han, Kavel Rao, Allyson Ettinger +5
We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety ris…