English
Related papers

Related papers: ENCORE: Entropy-guided Reward Composition for Mult…

200 papers

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally…

Machine Learning · Computer Science 2026-03-09 Azza Jenane , Nassim Walha , Lukas Kuhn , Florian Buettner

In reinforcement learning, two objective functions have been developed extensively in the literature: discounted and averaged rewards. The generalization to an entropy-regularized setting has led to improved robustness and exploration for…

Machine Learning · Computer Science 2025-01-20 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

Computation and Language · Computer Science 2026-02-06 Hongze Tan , Zihan Wang , Jianfei Pan , Jinghao Lin , Hao Wang , Yifan Wu , Tao Chen , Zhihang Zheng , Zhihao Tang , Haihua Yang

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

Machine Learning · Computer Science 2026-03-04 Amirhossein Afsharrad , Ruida Zhou , Luca Viano , Sanjay Lall , Mohammad Ghavamzadeh

Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more helpful and harmless responses. Reward models are trained as…

Reinforcement Learning with Verifiable Rewards (RLVR) for large language models (LLMs) has achieved remarkable progress in enhancing LLMs' reasoning capabilities on tasks with clear correctness criteria, such as mathematical reasoning…

Artificial Intelligence · Computer Science 2025-09-30 Guanxu Chen , Yafu Li , Yuxian Jiang , Chen Qian , Qihan Ren , Jingyi Yang , Yu Cheng , Dongrui Liu , Jing Shao

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

Computation and Language · Computer Science 2024-04-09 Bowen Qin , Duanyu Feng , Xi Yang

Since the debut of DPO, it has been shown that aligning a target LLM with human preferences via the KL-constrained RLHF loss is mathematically equivalent to a special kind of reward modeling task. Concretely, the task requires: 1) using the…

Machine Learning · Computer Science 2024-12-19 Yuzhong Hong , Hanshan Zhang , Junwei Bao , Hongfei Jiang , Yang Song

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

Artificial Intelligence · Computer Science 2025-09-24 Jingyan Shen , Jiarui Yao , Rui Yang , Yifan Sun , Feng Luo , Rui Pan , Tong Zhang , Han Zhao

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…

Machine Learning · Computer Science 2025-10-29 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion models. In this paper, we study reward guidance for discrete diffusion language models; now, one…

Machine Learning · Computer Science 2026-05-14 Atula Tejaswi , Litu Rout , Constantine Caramanis , Sanjay Shakkottai , Sujay Sanghavi

Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely opaque. In this work, we present Sparse Autoencoder For…

Computation and Language · Computer Science 2026-02-02 Wei Shi , Ziyuan Xie , Sihang Li , Xiang Wang

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Machine Learning · Computer Science 2026-01-21 Nyal Patel , Matthieu Bou , Arjun Jagota , Satyapriya Krishna , Sonali Parbhoo

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…

Artificial Intelligence · Computer Science 2025-07-29 Xingcheng Xu

Entropy regularization is known to improve exploration in sequential decision-making problems. We show that this same mechanism can also lead to nearly unbiased and lower-variance estimates of the mean reward in the optimize-and-estimate…

Machine Learning · Computer Science 2022-08-26 Ben Chugg , Peter Henderson , Jacob Goldin , Daniel E. Ho

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and…

Computation and Language · Computer Science 2025-12-25 Jiayi Zhou , Jiaming Ji , Juntao Dai , Dong Li , Yaodong Yang

In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularisation) to randomise their actions in favor of exploration. This often makes it challenging…

Machine Learning · Computer Science 2025-06-04 Daniel Jarne Ornia , Giannis Delimpaltadakis , Jens Kober , Javier Alonso-Mora

Reinforcement learning from human feedback (RLHF) has been crucial in aligning large language models (LLMs) with human values. Traditionally, RLHF involves generating responses to a query and using a reward model to assign a reward to the…

Computation and Language · Computer Science 2024-12-04 Wenxuan Zhou , Shujian Zhang , Lingxiao Zhao , Tao Meng