When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationMisinformationSimilar Papers 제목 키워드 기반
The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind
We investigate strategic deception in large language models using two complementary testbeds: Secret Agenda (across 38 models) and Insider Trading compliance (via SAE architectures). Secret Agenda reliably induced lying …
ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems
Recent advances in ID-free recommender systems have attracted significant attention for effectively addressing the cold start problem. However, their vulnerability to malicious attacks remains largely unexplored. In this…
Recommendation SystemsWerewolf Arena: A Case Study in LLM Evaluation via Social Deduction
This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, nav…
Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL
An increasingly prevalent socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help det…
counterfactualDeception DetectionDecision MakingFriction+3Deception in Reinforced Autonomous Agents
We explore the ability of large language model (LLM)-based agents to engage in subtle deception such as strategically phrasing and intentionally manipulating information to misguide and deceive other agents. This harmful…
Deception DetectionHallucinationLanguage ModelingLanguage Modelling+2