arXiv AI June 10, 2026 By Polydoros Giannouris, Mohsinul Kabir, Sophia Ananiadou

Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs

arXiv:2606. 10852v1 Announce Type: cross Abstract: LLM deception is often evaluated through direct markers such as fabricated claims, explicit lies, or strategic concealment.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 24

Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception

arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.

By Ali Asad, Stephen Obadinma, Anshul Pattoo, Wenxuan Zhang, Xiaodan Zhu

llms fine-tuning benchmarks safety

arXiv AI

Jun 17

Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing

arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.

By Kexin Chen, Yi Liu, Haonan Zhang, Yanhui Li, Xinyu Deng, Dongxia Wang

llms safety

arXiv AI

Jun 8

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry

arXiv:2603. 26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical.

By Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Lang Qin, Juntao Dai, Yaodong Yang, Jingwei Yi

llms reinforcement-learning safety

arXiv AI

Jul 24

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs

arXiv:2607. 20479v1 Announce Type: new Abstract: Training probes to detect deceptive outputs from large language models is still an open problem.

By Amr Moustafa, Max Feser, Florian Mai

llms efficiency benchmarks

arXiv AI

Jun 30

Safety from Honesty in a Disinterested AI Predictor

arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.

By Yoshua Bengio, Oliver Richardson, Tom\'a\v{s} Gaven\v{c}iak, Michael Cohen, Rory Svarc, Damiano Fornasiere, Gael Gendron, David Hyland, Aton Kamanda, Adam Oberman, Francis Rhys Ward, Anna Gaven\v{c}iak, Jacob Livingston Slosser, Vincent Mai, Iulian Serban, Joumana Ghosn

agents efficiency safety

arXiv AI

Jun 19

One Probe Won't Catch Them All: Towards Targeted Deception Detection

arXiv:2602. 01425v2 Announce Type: replace Abstract: Linear probes are a promising approach for monitoring AI systems for deceptive behaviour.

By Vikram Natarajan, Devina Jain, Shivam Arora, Satvik Golechha, Joseph Bloom

Related stories

Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception

Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs

Safety from Honesty in a Disinterested AI Predictor

One Probe Won't Catch Them All: Towards Targeted Deception Detection