中文
相关论文

相关论文: How to Catch an AI Liar: Lie Detection in Black-Bo…

200 篇论文

Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements. Hence, it is of interest and…

计算与语言 · 计算机科学 2024-10-22 Lennart Bürger , Fred A. Hamprecht , Boaz Nadler

Using AI to create autonomous researchers has the potential to accelerate scientific discovery. A prerequisite for this vision is understanding how well an AI model can identify the underlying structure of a black-box system from its…

机器学习 · 计算机科学 2025-05-26 Jiayi Geng , Howard Chen , Dilip Arumugam , Thomas L. Griffiths

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

Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses intermittently, which impedes the LLMs' reliability for further…

计算与语言 · 计算机科学 2024-03-22 Yukun Zhao , Lingyong Yan , Weiwei Sun , Guoliang Xing , Chong Meng , Shuaiqiang Wang , Zhicong Cheng , Zhaochun Ren , Dawei Yin

Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generate statements they believe are false. However, these techniques are typically validated in narrow settings that do not capture the…

计算与语言 · 计算机科学 2026-01-12 Kieron Kretschmar , Walter Laurito , Sharan Maiya , Samuel Marks

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

机器学习 · 计算机科学 2025-12-02 Dylan Sam , Marc Finzi , J. Zico Kolter

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…

计算与语言 · 计算机科学 2024-10-14 Rohan Ajwani , Shashidhar Reddy Javaji , Frank Rudzicz , Zining Zhu

We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model by estimating a numeric confidence score for any output it generated. Our uncertainty quantification technique works for any…

计算与语言 · 计算机科学 2023-10-05 Jiuhai Chen , Jonas Mueller

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

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

Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional…

机器学习 · 计算机科学 2025-09-04 Haoran Huan , Mihir Prabhudesai , Mengning Wu , Shantanu Jaiswal , Deepak Pathak

Large Language Models (LLMs) offer a promising approach to enhancing Explainable AI (XAI) by transforming complex machine learning outputs into easy-to-understand narratives, making model predictions more accessible to users, and helping…

人工智能 · 计算机科学 2025-04-02 Ahsan Bilal , David Ebert , Beiyu Lin

Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no…

人工智能 · 计算机科学 2026-04-08 Xiaotian Zhou , Di Tang , Xiaofeng Wang , Xiaozhong Liu

Large Language Models (LLMs) have demonstrated an alarming ability to impersonate humans in conversation, raising concerns about their potential misuse in scams and deception. Humans have a right to know if they are conversing to an LLM. We…

计算与语言 · 计算机科学 2024-12-23 Gilad Gressel , Rahul Pankajakshan , Yisroel Mirsky

Several recent works argue that LLMs have a universal truth direction where true and false statements are linearly separable in the activation space of the model. It has been demonstrated that linear probes trained on a single hidden state…

计算与语言 · 计算机科学 2025-05-16 Timour Ichmoukhamedov , David Martens

While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the…

计算与语言 · 计算机科学 2023-10-18 Amos Azaria , Tom Mitchell

Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the…

计算与语言 · 计算机科学 2024-06-06 Thilo Hagendorff

Despite their widespread use in fact-checking, moderation, and high-stakes decision-making, large language models (LLMs) remain poorly understood as judges of truth. This study presents the largest evaluation to date of LLMs' veracity…

计算与语言 · 计算机科学 2025-09-30 Emilio Barkett , Olivia Long , Madhavendra Thakur

We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but…

机器学习 · 计算机科学 2025-11-03 Bartosz Cywiński , Emil Ryd , Rowan Wang , Senthooran Rajamanoharan , Neel Nanda , Arthur Conmy , Samuel Marks

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…

人工智能 · 计算机科学 2025-06-06 Kai Wang , Yihao Zhang , Meng Sun
‹ 上一页 1 2 3 10 下一页 ›