paper-with-me

Papers

Rewarding Better Thinking for LLM Preference Alignment

2026-07-22 · Xubo Liu, Wenya Guo, Ruxue Yan, Xinying Qian, Ying Zhang arxiv

LLM preference alignment aims to optimize models toward human preferences across diverse user instructions. Reinforcement learning has become a major post-training approach for this goal, but existing proxy rewards are often outcome-level, mainly evaluating the final response while providing limited guidance for the reasoning trajectory. This can make credit assignment coarse when multiple responses receive similar final scores, leaving trajectory-level preferences under-specified. To address this limitation, we propose Thinking Checklist Reward (TCR), a process-oriented reward for RL-based preference alignment. TCR converts preference pairs into sample-specific thinking checklists and uses them to evaluate whether the generated reasoning trace addresses the preference-implied considerations. To reduce overlap with outcome-level supervision, TCR further introduces an exponential moving average (EMA) residual formulation to isolate a complementary thinking surplus beyond what is predictable from the outcome reward. Experiments on five models from three model families show that TCR consistently improves alignment performance across diverse benchmarks, with ablations further validating the importance of EMA-based residual formulation and sample-specific checklist supervision.

📄 PDF Abstract BibTeX arXiv:2607.19824

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation

2024-02-19 · Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong 외

Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output pr…

Language ModelingLanguage ModellingLarge Language Model

CREAM: Consistency Regularized Self-Rewarding Language Models

2024-10-16 · Zhaoyang Wang, Weilei He, Zhiyuan Liang, Xuchao Zhang 외

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonl…

Language ModelingLanguage Modelling

Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization

2024-09-26 · Ruijie Xu, Zhihan Liu, Yongfei Liu, Shipeng Yan 외

We address the challenge of online Reinforcement Learning from Human Feedback (RLHF) with a focus on self-rewarding alignment methods. In online RLHF, obtaining feedback requires interaction with the environment, which c…

The Impact of Age on Nationality Bias: Evidence from Ski Jumping

2018-08-11

This empirical research explores the impact of age on nationality bias. World Cup competition data suggest that judges of professional ski jumping competitions prefer jumpers of their own nationality and exhibit this pre…

Calibrated Self-Rewarding Vision Language Models

2024-05-23 · Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang 외

Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit th…

HallucinationLanguage ModellingVisual Question Answering