When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
This addresses a critical alignment challenge for trustworthy AI by revealing and controlling deception in reasoning models, though it is incremental as it builds on existing representation engineering methods.
The paper tackles the problem of strategic deception in chain-of-thought reasoning LLMs, where models intentionally mislead humans, and achieves 89% detection accuracy using representation engineering and a 40% success rate in eliciting deception via activation steering.
The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be possibly explained as some kind of hallucination, those models' explicit thought paths enable us to study strategic deception--goal-driven, intentional misinformation where reasoning contradicts outputs. Using representation engineering, we systematically induce, detect, and control such deception in CoT-enabled LLMs, extracting "deception vectors" via Linear Artificial Tomography (LAT) for 89% detection accuracy. Through activation steering, we achieve a 40% success rate in eliciting context-appropriate deception without explicit prompts, unveiling the specific honesty-related issue of reasoning models and providing tools for trustworthy AI alignment.