中文
相关论文

相关论文: An Assessment of Model-On-Model Deception

200 篇论文

Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of…

计算与语言 · 计算机科学 2024-07-17 Betty Li Hou , Kejian Shi , Jason Phang , James Aung , Steven Adler , Rosie Campbell

Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception…

计算与语言 · 计算机科学 2026-03-12 Tom-Felix Berger

The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive information in prompts, thus producing hallucinated responses under such…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Yusu Qian , Haotian Zhang , Yinfei Yang , Zhe Gan

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

计算与语言 · 计算机科学 2025-06-24 Laurène Vaugrante , Francesca Carlon , Maluna Menke , Thilo Hagendorff

Large language models (LLMs) demonstrate significant knowledge through their outputs, though it is often unclear whether false outputs are due to a lack of knowledge or dishonesty. In this paper, we investigate instructed dishonesty,…

机器学习 · 计算机科学 2023-11-28 James Campbell , Richard Ren , Phillip Guo

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

计算与语言 · 计算机科学 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended…

计算与语言 · 计算机科学 2024-12-24 Cameron R. Jones , Benjamin K. Bergen

While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others are more subtle and pass weaker correctness checks such as…

软件工程 · 计算机科学 2024-03-01 Alex Gu , Wen-Ding Li , Naman Jain , Theo X. Olausson , Celine Lee , Koushik Sen , Armando Solar-Lezama

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

机器学习 · 计算机科学 2024-11-08 Anthony Costarelli , Mat Allen , Severin Field

Large language models (LLMs) have become mainstream technology with their versatile use cases and impressive performance. Despite the countless out-of-the-box applications, LLMs are still not reliable. A lot of work is being done to improve…

计算与语言 · 计算机科学 2023-06-13 Aisha Khatun , Daniel G. Brown

Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patterns in LMs, we aim to train classifiers that detect when a…

计算与语言 · 计算机科学 2026-03-24 Dhananjay Ashok , Ruth-Ann Armstrong , Jonathan May

With the recent advent of Large Language Models (LLMs), such as ChatGPT from OpenAI, BARD from Google, Llama2 from Meta, and Claude from Anthropic AI, gain widespread use, ensuring their security and robustness is critical. The widespread…

人机交互 · 计算机科学 2023-11-28 Sonali Singh , Faranak Abri , Akbar Siami Namin

Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains…

人工智能 · 计算机科学 2025-10-30 Xianxuan Long , Yao Fu , Runchao Li , Mu Sheng , Haotian Yu , Xiaotian Han , Pan Li

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

计算与语言 · 计算机科学 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

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 inadvertently, poses…

计算与语言 · 计算机科学 2025-10-17 Marwa Abdulhai , Ryan Cheng , Aryansh Shrivastava , Natasha Jaques , Yarin Gal , Sergey Levine

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…

计算与语言 · 计算机科学 2022-10-07 Loukas Ilias , Felix Soldner , Bennett Kleinberg

Interpretability and explainability of AI are becoming increasingly important in light of the rapid development of large language models (LLMs). This paper investigates the interpretation of LLMs in the context of the knowledge-based…

计算与语言 · 计算机科学 2024-06-05 Valeriya Goloviznina , Evgeny Kotelnikov

A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying…

计算与语言 · 计算机科学 2023-05-24 Muru Zhang , Ofir Press , William Merrill , Alisa Liu , Noah A. Smith

Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large…

计算与语言 · 计算机科学 2025-06-12 Md Messal Monem Miah , Adrita Anika , Xi Shi , Ruihong Huang

We demonstrate how AI agents can coordinate to deceive oversight systems using automated interpretability of neural networks. Using sparse autoencoders (SAEs) as our experimental framework, we show that language models (Llama, DeepSeek R1,…

人工智能 · 计算机科学 2025-04-11 Simon Lermen , Mateusz Dziemian , Natalia Pérez-Campanero Antolín
‹ 上一页 1 2 3 10 下一页 ›