English
Related papers

Related papers: Linking Process to Outcome: Conditional Reward Mod…

200 papers

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…

Computation and Language · Computer Science 2025-10-09 Elle

Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning with verifiable rewards. However, LRMs often suffer from overthinking, expending excessive computation on…

Artificial Intelligence · Computer Science 2025-08-19 Chuhuai Yue , Chengqi Dong , Yinan Gao , Hang He , Jiajun Chai , Guojun Yin , Wei Lin

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their integration into multimodal reasoning remains largely…

Computation and Language · Computer Science 2025-10-07 Ruilin Luo , Zhuofan Zheng , Yifan Wang , Xinzhe Ni , Zicheng Lin , Songtao Jiang , Yiyao Yu , Chufan Shi , Lei Wang , Ruihang Chu , Jin Zeng , Yujiu Yang

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By…

Computation and Language · Computer Science 2026-03-05 Daniel Fein , Max Lamparth , Violet Xiang , Mykel J. Kochenderfer , Nick Haber

Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human preferences are vulnerable to reward hacking and generalize…

Machine Learning · Computer Science 2025-10-24 Zhenghao Xu , Qin Lu , Qingru Zhang , Liang Qiu , Ilgee Hong , Changlong Yu , Wenlin Yao , Yao Liu , Haoming Jiang , Lihong Li , Hyokun Yun , Tuo Zhao

Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative…

Computation and Language · Computer Science 2026-04-08 Ahsan Bilal , Ahmed Mohsin , Muhammad Umer , Ali Subhan , Hassan Rizwan , Ayesha Mohsin , Dean Hougen

Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal…

Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework that constrains…

Computation and Language · Computer Science 2025-11-12 Tangrui Li , Pei Wang , Hongzheng Wang Christian Hahm , Matteo Spatola , Justin Shi

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address…

Computation and Language · Computer Science 2025-06-03 Jiawei Gu , Shangsong Liang

Large language models have demonstrated remarkable capabilities in complex mathematical reasoning tasks, but they inevitably generate errors throughout multi-step solutions. Process-level Reward Models (PRMs) have shown great promise by…

Artificial Intelligence · Computer Science 2025-08-05 Jiuzhou Han , Wray Buntine , Ehsan Shareghi

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

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

Computation and Language · Computer Science 2026-03-25 Ruidi Chang , Jiawei Zhou , Hanjie Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Machine Learning · Computer Science 2025-10-21 Guofu Xie , Yunsheng Shi , Hongtao Tian , Ting Yao , Xiao Zhang

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Computation and Language · Computer Science 2025-10-30 Ziyou Hu , Zhengliang Shi , Minghang Zhu , Haitao Li , Teng Sun , Pengjie Ren , Suzan Verberne , Zhaochun Ren

Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…

Computation and Language · Computer Science 2026-02-12 Zhimin Hu , Riya Roshan , Sashank Varma

Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step by step" approaches, the field has evolved in two main…

Computation and Language · Computer Science 2025-07-25 Andreea Nica , Ivan Zakazov , Nicolas Mario Baldwin , Saibo Geng , Robert West

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…

Computation and Language · Computer Science 2025-01-15 Zhongxiang Sun , Qipeng Wang , Weijie Yu , Xiaoxue Zang , Kai Zheng , Jun Xu , Xiao Zhang , Song Yang , Han Li

Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process…

Machine Learning · Computer Science 2026-05-21 Xian Wu , Kaijie Zhu , Ying Zhang , Lun Wang , Wenbo Guo

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications…

Machine Learning · Computer Science 2026-05-18 Mehul Damani , Isha Puri , Stewart Slocum , Idan Shenfeld , Leshem Choshen , Yoon Kim , Jacob Andreas