Tianyuan Shi, Canbin Huang, Fanqi Wan, Longguang Zhong, Ziyi Yang, Weizhou Shen, Xiaojun Quan, Ming Yan
| Challenge: | Experimental results show that this iterative approach leads to consistent improvements in both the policy model and reward model. |
| Approach: | They propose a method that iteratively improves both the policy model and reward model without requiring additional human annotation. |
| Outcome: | The proposed method improves both the policy model and reward model without human annotation. |
Similar Papers
Semi-Supervised Reward Modeling via Iterative Self-Training (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reward models capture values and preferences of humans and are used in Reinforcement Learning with Human Feedback (RLHF) Traditionally, training large language models relies on extensive human-annotated preference data, which poses significant challenges in terms of scalability and cost. |
| Approach: | They propose a method that enhances RM training using unlabeled data. |
| Outcome: | The proposed approach improves reward models without incurring additional labeling costs on unlabeled datasets. |
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards (2026.acl-industry)
Copied to clipboard
| Challenge: | a large language model (LLM) is used as a business development agent for persuasive price negotiation in online travel agencies. |
| Approach: | They propose a reward-enhancing policy optimization method that integrates three complementary reward sources-a preference-trained reward model and an LLM-as-a-judge. |
| Outcome: | The proposed method improves average dialogue rating to 4.63 (+0.33 over GRPO) and raises share of conversations with at least one excellent response to 66.67% (+23.34 pp over grepo). |
Fine-Tuning Language Models with Reward Learning on Policy (2024.naacl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is an effective approach to align large language models (LLMs) to human preferences. |
| Approach: | They propose a framework that refines a reward model using policy samples to keep it on-distribution. |
| Outcome: | The proposed framework outperforms the state-of-the-art on three benchmark datasets showing that it can learn robust representations of policy samples. |
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. |
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing failure discovery methods rely on prior knowledge of preference attributes . Existing methods do not scale to new models or data. |
| Approach: | They propose a preference distribution agnostic procedure that uses the reward model itself to guide controlled decoding toward mis specified responses while preserving the underlying preference class. |
| Outcome: | The proposed procedure improves robustness without degrading reward quality across models. |
Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play Training (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models show impressive performance in a wide range of linguistic tasks, but their performance on complex reasoning tasks is still signif-icantly lower than the human level. |
| Approach: | They propose a reinforcement learning framework to synchronize the reasoning and critique capabilities of language models by using Monte Carlo sampling to give appropriate rewards to the model's critique content. |
| Outcome: | The proposed framework improves the model's reasoning and critique capabilities by 5.40 and 3.66 points, respectively, compared to the best baseline approach. |
PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to align large language models with human preferences are limited by their large-scale annotation and prone to reward overoptimization. |
| Approach: | They propose a training paradigm that integrates three complementary strategies to address these challenges by reformulating question–answer pairs into preference-task instructions, averaging the rewards aggregated from diverse preference- task instructions for each sample, and a balancing outputs from the value head under different dropout rates. |
| Outcome: | Experiments on public datasets show that PIRA improves performance considerably, enhances generalization, and effectively mitigates reward overoptimization. |
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for reinforcement learning with verifiable rewards (RLVR) rely on static objective functions and rigid clipping strategies that misalign with the model’s evolving reasoning capabilities. |
| Approach: | They propose to incorporate Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC) to overcome limitations of static mechanisms. |
| Outcome: | Extensive experiments on nine reasoning tasks show the proposed paradigm outperforms state-of-the-art methods. |
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences. |
| Approach: | They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data. |
| Outcome: | The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark . |
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. |