English
Related papers

Related papers: Stop Rewarding Hallucinated Steps: Faithfulness-Aw…

200 papers

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

This review examines the means with which faithfulness has been evaluated across open-ended summarization, question-answering and machine translation tasks. We find that the use of LLMs as a faithfulness evaluator is commonly the metric…

Computation and Language · Computer Science 2025-09-18 Ben Malin , Tatiana Kalganova , Nikoloas Boulgouris

When a language model answers a table question, users have no way to verify which cells informed which reasoning steps. We introduce RSAT, a method that trains small language models (SLMs, 1-8B) to produce step-by-step reasoning with…

Computation and Language · Computer Science 2026-05-08 Jugal Gajjar , Kamalasankari Subramaniakuppusamy

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupported information or contradictions even when provided with…

Computation and Language · Computer Science 2025-11-07 Manveer Singh Tamber , Forrest Sheng Bao , Chenyu Xu , Ge Luo , Suleman Kazi , Minseok Bae , Miaoran Li , Ofer Mendelevitch , Renyi Qu , Jimmy Lin

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

Machine Learning · Computer Science 2026-03-02 Zheng Zhang , Ziwei Shan , Kaitao Song , Yexin Li , Kan Ren

Large language models (LLMs) face significant challenges in effectively leveraging sequential environmental feedback (EF) signals, such as natural language evaluations, for feedback-independent chain-of-thought (CoT) reasoning. Existing…

Computation and Language · Computer Science 2025-07-29 Kang Yang , Jingxue Chen , Qingkun Tang , Tianxiang Zhang , Qianchun Lu

Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general-domain data and struggle with the structured, symbolic, and fact-sensitive nature of…

Computation and Language · Computer Science 2026-05-05 Jie Zhu , Yuanchen Zhou , Shuo Jiang , Junhui Li , Lifan Guo , Feng Chen , Chi Zhang

Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning begins? We introduce the Step-Level Reasoning Capacity…

Computation and Language · Computer Science 2026-04-14 Abhinaba Basu , Pavan Chakraborty

While Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to generate contextually grounded responses, contextual faithfulness remains challenging as LLMs may not consistently trust provided context, leading to…

Computation and Language · Computer Science 2026-02-10 Yongchao Long , Xian Wu , Yingying Zhang , Xianbin Wen , Yuxi Zhou , Shenda Hong

Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LLMs detect limited…

Machine Learning · Computer Science 2025-10-15 Zhongwei Yu , Wannian Xia , Xue Yan , Bo Xu , Haifeng Zhang , Yali Du , Jun Wang

Reinforcement learning (RL) has proven effective in incentivizing the reasoning abilities of large language models (LLMs), but suffers from severe efficiency challenges due to its trial-and-error nature. While the common practice employs…

Computation and Language · Computer Science 2025-10-17 Liang Chen , Xueting Han , Li Shen , Jing Bai , Kam-Fai Wong

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the…

Artificial Intelligence · Computer Science 2025-05-30 Zidi Xiong , Shan Chen , Zhenting Qi , Himabindu Lakkaraju

Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Tong Wei , Yijun Yang , Junliang Xing , Yuanchun Shi , Zongqing Lu , Deheng Ye

Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models,…

Artificial Intelligence · Computer Science 2025-10-30 Yuyuan Zeng , Yufei Huang , Can Xu , Qingfeng Sun , Jianfeng Yan , Guanghui Xu , Tao Yang , Fengzong Lian

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…

Machine Learning · Computer Science 2026-03-24 Kwanyoung Kim , Byeongsu Sim

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Artificial Intelligence · Computer Science 2026-05-19 Claudio Fanconi , Nicolás Astorga , Mihaela van der Schaar

To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that…

Computation and Language · Computer Science 2026-01-08 Jinbo Hao , Kai Yang , Qingzhen Su , Yifan Li , Chao Jiang

Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…

Computation and Language · Computer Science 2025-06-25 C. Nicolò De Sabbata , Theodore R. Sumers , Badr AlKhamissi , Antoine Bosselut , Thomas L. Griffiths