English
Related papers

Related papers: Evaluating Reward Model Generalization via Pairwis…

200 papers

In robust Markov decision processes (MDPs), the uncertainty in the transition kernel is addressed by finding a policy that optimizes the worst-case performance over an uncertainty set of MDPs. While much of the literature has focused on…

Machine Learning · Computer Science 2023-03-02 Yue Wang , Alvaro Velasquez , George Atia , Ashley Prater-Bennette , Shaofeng Zou

Multi-environment POMDPs (ME-POMDPs) extend standard POMDPs with discrete model uncertainty. ME-POMDPs represent a finite set of POMDPs that share the same state, action, and observation spaces, but may arbitrarily vary in their transition,…

Artificial Intelligence · Computer Science 2025-10-29 Eline M. Bovy , Caleb Probine , Marnix Suilen , Ufuk Topcu , Nils Jansen

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Reinforcement learning from human feedback (RLHF) is a critical technique for training large language models. However, conventional reward models based on the Bradley-Terry model (BTRM) often suffer from overconfidence when faced with…

Machine Learning · Computer Science 2025-05-19 Wangtao Sun , Xiang Cheng , Xing Yu , Haotian Xu , Zhao Yang , Shizhu He , Jun Zhao , Kang Liu

Assessing an AI agent that can converse in human language and understand visual content is challenging. Generation metrics, such as BLEU scores favor correct syntax over semantics. Hence a discriminative approach is often used, where an…

Artificial Intelligence · Computer Science 2021-08-05 Idan Schwartz

In the deployment of large language models (LLMs), accurate confidence estimation is critical for assessing the credibility of model predictions. However, existing methods often fail to overcome the issue of overconfidence on incorrect…

Computation and Language · Computer Science 2024-02-20 Pei Wang , Yejie Wang , Muxi Diao , Keqing He , Guanting Dong , Weiran Xu

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably…

Computation and Language · Computer Science 2026-02-10 Haoran Zhang , Yafu Li , Zhi Wang , Zhilin Wang , Shunkai Zhang , Xiaoye Qu , Yu Cheng

Process Reward Models (PRMs), which assign fine-grained scores to intermediate reasoning steps within a solution trajectory, have emerged as a promising approach to enhance the reasoning quality of Large Language Models (LLMs). However,…

Computation and Language · Computer Science 2026-01-07 Lingyin Zhang , Jun Gao , Xiaoxue Ren , Ziqiang Cao

The integration of large language models (LLMs) into medical practice offers transformative potential, yet their real-world clinical applicability remains constrained by critical alignment issues: (1) a misalignment between static…

Artificial Intelligence · Computer Science 2025-12-05 Yongnan Jin , Xurui Li , Feng Cao , Liucun Gao , Juanjuan Yao

We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter…

Optimization and Control · Mathematics 2020-08-19 Tien Mai , Patrick Jaillet

Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability;…

Machine Learning · Statistics 2026-01-30 Mingyuan Xu , Xinzi Tan , Jiawei Wu , Doudou Zhou

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

Computation and Language · Computer Science 2025-09-26 Zijun Liu , Peiyi Wang , Runxin Xu , Shirong Ma , Chong Ruan , Peng Li , Yang Liu , Yu Wu

Reinforcement Learning from Human Feedback has emerged as a standard for aligning diffusion models. However, we identify a fundamental limitation in the standard DPO formulation because it relies on the Bradley-Terry model to aggregate…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Jiho Jang , Jinyoung Kim , Kyungjune Baek , Nojun Kwak

Reward models (RMs) are crucial for the training of large language models (LLMs), yet they typically rely on large-scale human-annotated preference pairs. With the widespread deployment of LLMs, in-the-wild interactions have emerged as a…

Computation and Language · Computer Science 2026-02-10 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Lei Hou , Juanzi Li

Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short in expressiveness, particularly in addressing intransitive…

Artificial Intelligence · Computer Science 2025-06-12 Yifan Zhang , Ge Zhang , Yue Wu , Kangping Xu , Quanquan Gu

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric…

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…

Artificial Intelligence · Computer Science 2019-12-06 Maor Gaon , Ronen I. Brafman

Evaluation using Large Language Model (LLM) judges has been widely adopted in English and shown to be effective for automatic evaluation. However, their performance does not generalize well to non-English settings, and it remains unclear…

Computation and Language · Computer Science 2026-01-29 David Anugraha , Shou-Yi Hung , Zilu Tang , Annie En-Shiun Lee , Derry Tanti Wijaya , Genta Indra Winata

Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Jie Wu , Yu Gao , Zilyu Ye , Ming Li , Liang Li , Hanzhong Guo , Jie Liu , Zeyue Xue , Xiaoxia Hou , Wei Liu , Yan Zeng , Weilin Huang

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

Social and Information Networks · Computer Science 2025-07-01 Minnan Wei , Ziming Li , Xiang Chen , Menglin Zheng , Ziyan Qu , Cheng Yu , Siyu Chen , Xiaolin Ju