English
Related papers

Related papers: On-Policy Self-Alignment with Fine-grained Knowled…

200 papers

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this…

Large Language Models (LLMs) have demonstrated remarkable fluency across a range of natural language tasks, yet remain vulnerable to hallucinations - factual inaccuracies that undermine trust in real world deployment. We present…

Computation and Language · Computer Science 2025-07-16 Kaushik Dwivedi , Padmanabh Patanjali Mishra

Large Language Models (LLMs) possess a remarkable capacity to generate persuasive and intelligible language. However, coherence does not equate to truthfulness, as the responses often contain subtle hallucinations. Existing benchmarks are…

Computation and Language · Computer Science 2026-02-24 Alex Robertson , Huizhi Liang , Mahbub Gani , Rohit Kumar , Srijith Rajamohan

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To address these challenges, we propose a retrieval-augmented…

Computation and Language · Computer Science 2025-07-22 Ashley Lewis , Michael White , Jing Liu , Toshiaki Koike-Akino , Kieran Parsons , Ye Wang

In modern dialogue systems, the use of Large Language Models (LLMs) has grown exponentially due to their capacity to generate diverse, relevant, and creative responses. Despite their strengths, striking a balance between the LLMs'…

Computation and Language · Computer Science 2023-08-01 Chen Zhang

While Large Language Models (LLM) are able to accumulate and restore knowledge, they are still prone to hallucination. Especially when faced with factual questions, LLM cannot only rely on knowledge stored in parameters to guarantee…

Computation and Language · Computer Science 2024-01-04 Pierre Erbacher , Louis Falissar , Vincent Guigue , Laure Soulier

Recent advances in natural language processing (NLP), particularly large language models (LLMs), have motivated the automatic translation of natural language statements into formal logic without human intervention. This enables automated…

Computation and Language · Computer Science 2025-12-03 Muyu Pan , Dheeraj Kodakandla , Mahfuza Farooque

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Computation and Language · Computer Science 2025-08-05 Yijun Feng

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of…

Machine Learning · Computer Science 2025-12-30 Timo Kaufmann , Paul Weng , Viktor Bengs , Eyke Hüllermeier

Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research…

Computation and Language · Computer Science 2024-06-11 Weihang Su , Changyue Wang , Qingyao Ai , Yiran HU , Zhijing Wu , Yujia Zhou , Yiqun Liu

The prevalent use of large language models (LLMs) in various domains has drawn attention to the issue of "hallucination," which refers to instances where LLMs generate factually inaccurate or ungrounded information. Existing techniques for…

Computation and Language · Computer Science 2023-10-10 Junyu Luo , Cao Xiao , Fenglong Ma

Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research…

Machine Learning · Computer Science 2025-11-07 Raghav Sharma , Manan Mehta , Sai Tiger Raina

While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric…

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Machine Learning · Computer Science 2026-05-07 Etienne Gauthier , Francis Bach , Michael I. Jordan

Large Language Models (LLMs) have recently garnered widespread attention due to their adeptness at generating innovative responses to the given prompts across a multitude of domains. However, LLMs often suffer from the inherent limitation…

Computation and Language · Computer Science 2025-04-15 Sharanya Dasgupta , Sujoy Nath , Arkaprabha Basu , Pourya Shamsolmoali , Swagatam Das

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Computation and Language · Computer Science 2024-03-12 Yue Zhang , Leyang Cui , Wei Bi , Shuming Shi

Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Existing methods either rely on large-scale annotated data for fine-tuning, which incurs…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yu Zhang , Chuyang Sun , Kehai Chen , Xuefeng Bai , Yang Xiang , Min Zhang

Large Language Models (LLMs) have demonstrated strong capabilities in text-based tasks but struggle with the complex reasoning required for physics problems, particularly in advanced arithmetic and conceptual understanding. While some…

While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not align with the given visual input, which restricts their…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Ce Zhang , Zifu Wan , Zhehan Kan , Martin Q. Ma , Simon Stepputtis , Deva Ramanan , Russ Salakhutdinov , Louis-Philippe Morency , Katia Sycara , Yaqi Xie