But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors
Recent safety evaluations of Large Language Models (LLMs) show that many models exhibit dishonest behavior, such as sycophancy. However, most honesty benchmarks focus exclusively on factual knowledge or explicitly harmful behavior and rely on external judges, which are often unable to detect less obvious forms of dishonesty. In this work, we introduce a new framework, Judge Using Safety-Steered Alternatives (JUSSA), which utilizes steering vectors trained on a single sample to elicit more honest responses from models, helping LLM-judges in the detection of dishonest behavior. To test our framework, we introduce a new manipulation dataset with prompts specifically designed to elicit deceptive responses. We find that JUSSA enables LLM judges to better differentiate between dishonest and benign responses, and helps them identify subtle instances of manipulative behavior.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Survey on the Honesty of Large Language Models
Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite…
SurveyParametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data
Large language models (LLMs) are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing what they know and what they don't know. As a result, they can generate fa…
Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports alone these are indistinguishable, and rei…
Reinforcement LearningThe Impossibility of Eliciting Latent Knowledge
Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far) exceed that of their developers or users. Consequently, a desirable property for an AI system is that it is honest --…
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and automated grading. Such rubrics are reliable only if they reward honest ans…
Reinforcement Learning