English
Related papers

Related papers: Regularized Best-of-N Sampling with Minimum Bayes …

200 papers

Recent advances in diffusion language models (DLMs) have presented a promising alternative to traditional autoregressive large language models (LLMs). However, DLMs still lag behind LLMs in reasoning performance, especially as the number of…

Computation and Language · Computer Science 2025-10-27 Chenglong Wang , Yang Gan , Hang Zhou , Chi Hu , Yongyu Mu , Kai Song , Murun Yang , Bei Li , Chunliang Zhang , Tongran Liu , Jingbo Zhu , Zhengtao Yu , Tong Xiao

Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter alia). While these models do not explicitly…

Computation and Language · Computer Science 2022-11-02 Freda Shi , Daniel Fried , Marjan Ghazvininejad , Luke Zettlemoyer , Sida I. Wang

The growing safety concerns surrounding large language models raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints…

Artificial Intelligence · Computer Science 2024-11-25 Xinmeng Huang , Shuo Li , Edgar Dobriban , Osbert Bastani , Hamed Hassani , Dongsheng Ding

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Machine Learning · Computer Science 2025-05-20 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Dongha Lee , Jinyoung Yeo

Large language models (LLMs) are typically pretrained with next-word prediction (NWP), which yields strong surface fluency but places limited pressure on models to form explicit reasoning before emitting tokens. We study whether shifting…

Computation and Language · Computer Science 2025-09-30 Ming Shen , Zhikun Xu , Jacob Dineen , Xiao Ye , Ben Zhou

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

Reinforcement Learning (RL) suffers from sample inefficiency in sparse reward domains, and the problem is further pronounced in case of stochastic transitions. To improve the sample efficiency, reward shaping is a well-studied approach to…

Machine Learning · Computer Science 2024-10-10 Siddhant Bhambri , Amrita Bhattacharjee , Durgesh Kalwar , Lin Guan , Huan Liu , Subbarao Kambhampati

Reinforcement Learning algorithms that learn from human feedback (RLHF) need to be efficient in terms of statistical complexity, computational complexity, and query complexity. In this work, we consider the RLHF setting where the feedback…

Machine Learning · Computer Science 2024-03-14 Runzhe Wu , Wen Sun

Given the increasing importance of machine learning (ML) in our lives, several algorithmic fairness techniques have been proposed to mitigate biases in the outcomes of the ML models. However, most of these techniques are specialized to…

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has…

Machine Learning · Computer Science 2025-01-17 Ariel D. Procaccia , Benjamin Schiffer , Shirley Zhang

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RLHF) proves effective, it is complicated and highly…

Computation and Language · Computer Science 2024-10-31 Shiqi Wang , Zhengze Zhang , Rui Zhao , Fei Tan , Cam Tu Nguyen

Using the bit string generation problem as a case study, we theoretically compare two standard methods for adapting large language models to new tasks. The first, referred to as supervised fine-tuning, involves training a new next token…

Machine Learning · Statistics 2026-03-31 Seamus Somerstep , Vinod Raman , Unique Subedi , Yuekai Sun

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

Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional robust optimization. The key idea is to modify the…

Machine Learning · Computer Science 2020-06-08 Aurora Cobo Aguilera , Antonio Artés-Rodríguez , Fernando Pérez-Cruz , Pablo Martínez Olmos

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a challenge. While reranking could select the optimal output from multiple generated…

Computation and Language · Computer Science 2026-05-29 Riza Setiawan Soetedjo , Yusuke Sakai , Hidetaka Kamigaito , Jingun Kwon , Manabu Okumura , Taro Watanabe

Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective way to steer language models (LMs) toward preferred behaviors using reward models (RM). However, these approaches can be…

Computation and Language · Computer Science 2026-03-16 Vinod Raman , Hilal Asi , Satyen Kale

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Machine Learning · Computer Science 2026-02-13 Yihan Du , Seo Taek Kong , R. Srikant

Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback (RLHF), are typically cast as optimizing a tradeoff between…

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…

Machine Learning · Computer Science 2025-10-10 Chenxi Liu , Tianyi Xiong , Yanshuo Chen , Ruibo Chen , Yihan Wu , Junfeng Guo , Tianyi Zhou , Heng Huang