English
Related papers

Related papers: The Polite Liar: Epistemic Pathology in Language M…

200 papers

A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigate whether this human improvement strategy can be applied to…

Machine Learning · Computer Science 2025-12-17 Shicheng Liu , Siyuan Xu , Wenjie Qiu , Hangfan Zhang , Minghui Zhu

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through…

Computation and Language · Computer Science 2023-10-10 Zheng Yuan , Hongyi Yuan , Chuanqi Tan , Wei Wang , Songfang Huang , Fei Huang

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

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

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Large language models increasingly function as epistemic agents -- entities that can 1) autonomously pursue epistemic goals and 2) actively shape our shared knowledge environment. They curate the information we receive, often supplanting…

Artificial Intelligence · Computer Science 2026-03-24 Nahema Marchal , Stephanie Chan , Matija Franklin , Manon Revel , Geoff Keeling , Roberta Fischli , Bilva Chandra , Iason Gabriel

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Computation and Language · Computer Science 2024-03-29 Hao Lang , Fei Huang , Yongbin Li

Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article…

Machine Learning · Computer Science 2026-02-03 Vikram Krishnamurthy

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Machine Learning · Computer Science 2026-03-30 Kristiyan Haralambiev

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

Machine Learning · Computer Science 2024-04-22 Diego Calanzone , Stefano Teso , Antonio Vergari

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

Computation and Language · Computer Science 2024-07-12 Prasann Singhal , Tanya Goyal , Jiacheng Xu , Greg Durrett

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok

Language model families exhibit striking disparity in their capacity to benefit from reinforcement learning: under identical training, models like Qwen achieve substantial gains, while others like Llama yield limited improvements.…

Computation and Language · Computer Science 2026-01-13 Shaoning Sun , Mingzhu Cai , Huang He , Bingjin Chen , Siqi Bao , Yujiu Yang , Hua Wu , Haifeng Wang

In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…

Computation and Language · Computer Science 2024-05-21 William M. Hayes , Nicolas Yax , Stefano Palminteri

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…

Computation and Language · Computer Science 2024-12-24 Cameron R. Jones , Benjamin K. Bergen

Large Language Models (LLMs) are known to overuse certain terms like "delve" and "intricate." The exact reasons for these lexical choices, however, have been unclear. Using Meta's Llama model, this study investigates the contribution of…

Computation and Language · Computer Science 2025-08-05 Tom S. Juzek , Zina B. Ward

Empathy is central to human connection, yet people often struggle to express it effectively. In blinded evaluations, large language models (LLMs) generate responses that are often judged more empathic than human-written ones. Yet when a…

Computation and Language · Computer Science 2026-03-17 Aakriti Kumar , Nalin Poungpeth , Diyi Yang , Bruce Lambert , Matthew Groh

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over…

Machine Learning · Computer Science 2024-02-28 Gustaf Ahdritz , Tian Qin , Nikhil Vyas , Boaz Barak , Benjamin L. Edelman

In this paper, we study format biases in reinforcement learning from human feedback (RLHF). We observe that many widely-used preference models, including human evaluators, GPT-4, and top-ranking models on the RewardBench benchmark, exhibit…

Computation and Language · Computer Science 2025-05-26 Xuanchang Zhang , Wei Xiong , Lichang Chen , Tianyi Zhou , Heng Huang , Tong Zhang

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…

Computation and Language · Computer Science 2026-03-05 Anirudh Bharadwaj , Chaitanya Malaviya , Nitish Joshi , Mark Yatskar