English
Related papers

Related papers: Training LLMs for Honesty via Confessions

200 papers

People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishonesty in helpful and…

Computation and Language · Computer Science 2024-06-06 Youcheng Huang , Jingkun Tang , Duanyu Feng , Zheng Zhang , Wenqiang Lei , Jiancheng Lv , Anthony G. Cohn

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current…

Computation and Language · Computer Science 2024-09-30 Siheng Li , Cheng Yang , Taiqiang Wu , Chufan Shi , Yuji Zhang , Xinyu Zhu , Zesen Cheng , Deng Cai , Mo Yu , Lemao Liu , Jie Zhou , Yujiu Yang , Ngai Wong , Xixin Wu , Wai Lam

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising…

Machine Learning · Computer Science 2026-05-12 Renjie Gu , Jiazhen Du , Yihua Zhang , Sijia Liu

Large Language Models (LLMs) have achieved remarkable success across various industries due to their exceptional generative capabilities. However, for safe and effective real-world deployments, ensuring honesty and helpfulness is critical.…

Computation and Language · Computer Science 2024-12-12 Chujie Gao , Siyuan Wu , Yue Huang , Dongping Chen , Qihui Zhang , Zhengyan Fu , Yao Wan , Lichao Sun , Xiangliang Zhang

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

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To…

Computation and Language · Computer Science 2024-02-14 Ryan Liu , Theodore R. Sumers , Ishita Dasgupta , Thomas L. Griffiths

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Computation and Language · Computer Science 2026-03-03 David Bani-Harouni , Chantal Pellegrini , Paul Stangel , Ege Özsoy , Kamilia Zaripova , Nassir Navab , Matthias Keicher

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

Machine Learning · Computer Science 2026-05-15 Junyu Guo , Shangding Gu , Ming Jin , Costas Spanos , Javad Lavaei

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…

Computation and Language · Computer Science 2024-07-17 Betty Li Hou , Kejian Shi , Jason Phang , James Aung , Steven Adler , Rosie Campbell

Can large language models (LLMs) admit their mistakes when they should know better? In this work, we study when and why LLMs choose to retract, i.e., spontaneously and immediately acknowledge their errors. Using model-specific testbeds, we…

Computation and Language · Computer Science 2026-01-21 Yuqing Yang , Robin Jia

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

Computation and Language · Computer Science 2026-03-05 Xinyu Zhou , Chang Jin , Carsten Eickhoff , Zhijiang Guo , Seyed Ali Bahrainian

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- classifying whether a…

Machine Learning · Computer Science 2026-03-11 Helena Casademunt , Bartosz Cywiński , Khoi Tran , Arya Jakkli , Samuel Marks , Neel Nanda

Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications. Previous work elicits confidence from LLMs by direct or…

Computation and Language · Computer Science 2024-10-07 Tianyang Xu , Shujin Wu , Shizhe Diao , Xiaoze Liu , Xingyao Wang , Yangyi Chen , Jing Gao

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Computation and Language · Computer Science 2025-02-28 Yudi Zhang , Lu Wang , Meng Fang , Yali Du , Chenghua Huang , Jun Wang , Qingwei Lin , Mykola Pechenizkiy , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Computation and Language · Computer Science 2025-07-16 Pedro Ferreira , Wilker Aziz , Ivan Titov

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.…

Computation and Language · Computer Science 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Computation and Language · Computer Science 2025-05-21 Katie Matton , Robert Osazuwa Ness , John Guttag , Emre Kıcıman

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…

Computation and Language · Computer Science 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

Large language models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. While unintuitive from a classic view of LMs, recent work has shown that the truth…

Computation and Language · Computer Science 2024-02-07 Nitish Joshi , Javier Rando , Abulhair Saparov , Najoung Kim , He He
‹ Prev 1 2 3 10 Next ›