CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that rule-based evaluation methods are ineffective for open-ended natural language generation. |
| Approach: | They propose a pointwise generative reward model with a dedicated two-stage rollout method and unified query-based criteria that can be trained with 5.7K high-quality data. |
| Outcome: | The proposed model achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. |
Similar Papers
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reward models rely on scalar or pairwise judgments that fail to capture multifaceted nature of human preferences. |
| Approach: | They propose a rubric-based reward model that uses a large collection of prompt, rubric pairs to generate a scalar score or preference label for each response. |
| Outcome: | The proposed model surpasses strong size-matched baselines by 8.4% across multiple benchmarks. |
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)
Copied to clipboard
Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang
| Challenge: | Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation. |
| Approach: | They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward. |
| Outcome: | The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench. |
Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)
Copied to clipboard
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
| Challenge: | Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format. |
| Approach: | They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision. |
| Outcome: | The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges. |
EQA-RM: A Generative Embodied Reward Model with Test-time Scaling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing generic Reward Models are ill-equipped for dynamic and interactive domains. |
| Approach: | They propose a novel generative multimodal reward model specifically architected for EQA that provides interpretable, structured reward feedback. |
| Outcome: | The proposed model outperforms proprietary benchmarks, including Gemini-2.5-Flash, GPT-4o, Claude-3.5-Haiku, and open-sourced state-of-the-art models such as RoVRM and VisualPRM. |
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reward models lack generative and reasoning capabilities, resulting in poor performance. |
| Approach: | They propose a reward-aware task-adaptive reward model that enables pointwise training using readily available pairwise data via a novel Preference-Aware Reward mechanism. |
| Outcome: | The proposed reward model achieves an average relative improvement of 8.7% over the base models on RewardBench and RMBench. |
Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs. |
| Approach: | They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format . |
| Outcome: | The proposed model shows significant improvements over baselines on multiple human preference benchmarks. |
APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that RLHF improves performance of Large Language Models . BT-based RMs struggle to distinguish between similar preference responses . |
| Approach: | They propose to enhance BT-based reward models by using an adaptive margin mechanism . they use semantic similarity and reward-predicted reward differences to adjust focus . |
| Outcome: | Experimental results show that the proposed method outperforms existing methods in both in-distribution and OOD settings. |
Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck. |
| Approach: | They propose a framework that uses a generative verifier to provide soft, probabilistic rewards. |
| Outcome: | The proposed framework outperforms existing models up to 10x their size and can be scalable and effective. |
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models (2026.acl-long)
Copied to clipboard
Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao
| Challenge: | Reinforcement learning (RL) has improved text- and vision-language models, but its application in SDMs is hindered. |
| Approach: | They propose a dual-axis Generative Reward Model that provides semantic quality and interaction timing for SDMs. |
| Outcome: | The proposed model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets. |
Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards (2026.acl-srw)
Copied to clipboard
| Challenge: | Literature review systems generate literature review tables by inferring schemas and values from documents. |
| Approach: | They propose to use schema generation as a reinforcement learning problem to determine which dimensions to compare a set of papers. |
| Outcome: | The proposed model improves over the untuned model across intrinsic, reference-based, and LLM-judge metrics and remains competitive with supervised fine-tune models at 5 the parameter count on structural and diversity dimensions. |