paper-with-me

홈 › Papers

Disentangling Deception and Hallucination Failures in LLMs

2026-02-16 · Haolang Lu, Hongrui Peng, WeiYe Fu, Guoshun Nan, Xinye Cao, Xingrui Li, Hongcan Guo, Kun Wang arxiv

Failures in large language models (LLMs) are often analyzed from a behavioral perspective, where incorrect outputs in factual question answering are commonly associated with missing knowledge. In this work, focusing on entity-based factual queries, we suggest that such a view may conflate different failure mechanisms, and propose an internal, mechanism-oriented perspective that separates Knowledge Existence from Behavior Expression. Under this formulation, hallucination and deception correspond to two qualitatively different failure modes that may appear similar at the output level but differ in their underlying mechanisms. To study this distinction, we construct a controlled environment for entity-centric factual questions in which knowledge is preserved while behavioral expression is selectively altered, enabling systematic analysis of four behavioral cases. We analyze these failure modes through representation separability, sparse interpretability, and inference-time activation steering.

📄 PDF Abstract BibTeX arXiv:2602.14529

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

2025-06-05 · Kai Wang, Yihao Zhang, Meng Sun

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 L…

HallucinationMisinformation

Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL

2025-10-16 · Marwa Abdulhai, Ryan Cheng, Aryansh Shrivastava, Natasha Jaques 외 arxiv

Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare. However, their ability to produce deceptive outputs, whether intentionally or in…

Reinforcement Learning

Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses

2026-03-10 · Congning Ni, Sarvech Qadir, Bryan Steitz, Mihir Sachin Vaidya 외 arxiv

Mental health concerns are often expressed outside clinical settings, including in high-distress help seeking, where safety-critical guidance may be needed. Consumer health informatics systems increasingly incorporate la…

Question Answering

Deception in Reinforced Autonomous Agents

2024-05-07 · Atharvan Dogra, Krishna Pillutla, Ameet Deshpande, Ananya B Sai 외

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

Challenging Multilingual LLMs: A New Taxonomy and Benchmark for Unraveling Hallucination in Translation

2025-10-28 · Xinwei Wu, Heng Liu, Jiang Zhou, Xiaohu Zhao 외 arxiv

Large Language Models (LLMs) have advanced machine translation but remain vulnerable to hallucinations. Unfortunately, existing MT benchmarks are not capable of exposing failures in multilingual LLMs. To disclose halluci…

Machine Translation