English
Related papers

Related papers: Detecting Strategic Deception Using Linear Probes

200 papers

Text-based misinformation permeates online discourses, yet evidence of people's ability to discern truth from such deceptive textual content is scarce. We analyze a novel TV game show data where conversations in a high-stake environment…

Computation and Language · Computer Science 2024-04-09 Sanchaita Hazra , Bodhisattwa Prasad Majumder

This research critically navigates the intricate landscape of AI deception, concentrating on deceptive behaviours of Large Language Models (LLMs). My objective is to elucidate this issue, examine the discourse surrounding it, and…

Computation and Language · Computer Science 2024-03-18 Linge Guo

Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and erode…

Artificial Intelligence · Computer Science 2024-08-02 Valdemar Danry , Pat Pataranutaporn , Matthew Groh , Ziv Epstein , Pattie Maes

We investigate how low-quality AI advisors, lacking quality disclosures, can help spread text-based lies while seeming to help people detect lies. Participants in our experiment discern truth from lies by evaluating transcripts from a game…

Computation and Language · Computer Science 2025-02-04 Haimanti Bhattacharya , Subhasish Dugar , Sanchaita Hazra , Bodhisattwa Prasad Majumder

Whether an interviewee's honest and deceptive responses can be detected by facial expression signals in videos has been debated and requires further research. We developed deep learning models enabled by computer vision to extract temporal…

Human-Computer Interaction · Computer Science 2026-05-19 Hung-Yue Suen , Kuo-En Hung , Che-Wei Liu , Yu-Sheng Su , Han-Chih Fan

The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to…

Machine Learning · Computer Science 2026-01-29 Tianyi Alex Qiu , Micah Carroll , Cameron Allen

Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which a model appears aligned while covertly pursuing misaligned…

Artificial Intelligence · Computer Science 2025-05-27 Jiaming Ji , Wenqi Chen , Kaile Wang , Donghai Hong , Sitong Fang , Boyuan Chen , Jiayi Zhou , Juntao Dai , Sirui Han , Yike Guo , Yaodong Yang

Eliciting Latent Knowledge (ELK) aims to find patterns in a capable neural network's activations that robustly track the true state of the world, especially in hard-to-verify cases where the model's output is untrusted. To further ELK…

Machine Learning · Computer Science 2024-08-12 Alex Mallen , Madeline Brumley , Julia Kharchenko , Nora Belrose

Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam detection. We addressed this issue by creating a…

Cryptography and Security · Computer Science 2025-11-05 Chen-Wei Chang , Shailik Sarkar , Shutonu Mitra , Qi Zhang , Hossein Salemi , Hemant Purohit , Fengxiu Zhang , Michin Hong , Jin-Hee Cho , Chang-Tien Lu

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

People are not very good at detecting lies, which may explain why they refrain from accusing others of lying, given the social costs attached to false accusations - both for the accuser and the accused. Here we consider how this social…

General Economics · Economics 2022-12-09 Alicia von Schenk , Victor Klockmann , Jean-François Bonnefon , Iyad Rahwan , Nils Köbis

Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these…

Computation and Language · Computer Science 2023-12-08 Kevin Liu , Stephen Casper , Dylan Hadfield-Menell , Jacob Andreas

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly…

Computation and Language · Computer Science 2026-05-12 Aojie Yuan , Zhiyuan Julian Su , Haiyue Zhang , Yi Nian , Yue Zhao

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Artificial Intelligence · Computer Science 2026-05-26 Andreas Opedal , Francesco Ignazio Re , Abulhair Saparov , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

People are regularly confronted with potentially deceptive statements (e.g., fake news, misleading product reviews, or lies about activities). Only few works on automated text-based deception detection have exploited the potential of deep…

Computation and Language · Computer Science 2022-10-07 Loukas Ilias , Felix Soldner , Bennett Kleinberg

Deception plays critical roles in economics and technology, especially in emerging interactions in cyberspace. Holistic models of deception are needed in order to analyze interactions and to design mechanisms that improve them. Game theory…

Cryptography and Security · Computer Science 2018-04-19 Jeffrey Pawlick , Edward Colbert , Quanyan Zhu

We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assistant to complete, these tasks spanning writing assistance,…

Computation and Language · Computer Science 2024-05-06 Olli Järviniemi , Evan Hubinger

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral…

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…

Machine Learning · Computer Science 2025-07-15 Santhosh Kumar Ravindran