Verifying the Subjective: Structured Multilingual Rewards for Low-Resource Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Structured Multilingual Reward Modeling Framework extends Reinforcement Learning with Verifiable Rewards (RLVR) to subjective and open-ended tasks. |
| Approach: | They propose a framework that extends Reinforcement Learning with Verifiable Rewards to subjective and open-ended tasks. |
| Outcome: | The proposed framework improves reasoning capability and response quality on 7 tasks across 50 low-resource languages. |
Similar Papers
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. |
Demystifying Multilingual Reasoning in Process Reward Modeling (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study focuses on the use of large language models to solve multi-step reasoning tasks. |
| Approach: | They propose to extend large language models to multilingual settings by extending process reward models to English . they train multilingual PRMs on a dataset spanning seven languages, which is translated from english . |
| Outcome: | The proposed model improves accuracy and reduces early-stage reasoning errors. |
Check Your Work: Structured Checklist Feedback for Improving Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have been driven by verifiable feedback in deterministic domains like mathematics and code. |
| Approach: | They propose to decompose granular, prompt-specific checklists into a scalar reward and use them to transform them into skalar rewards. |
| Outcome: | The proposed approach yields an 11.8% win-rate improvement on AlpacaEval 2.0 using Qwen3-8B, outperforming holistic reward models and existing checklist baselines. |
Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic (2024.emnlp-main)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences, but the sparsity of these signals can lead to inefficient and unstable learning. |
| Approach: | They propose a framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards during RL training. |
| Outcome: | The proposed framework improves sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation. |
Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have shifted the post-training paradigm from instruction tuning and human preference alignment to reinforcement learning (RL) based on rule-based evaluations of answer correctness, these models often receive rewards for speculative answers without generating coherent reasoning chains. |
| Approach: | They propose a confidence-based reward model tailored for enhancing STEM reasoning capabilities. |
| Outcome: | The proposed model outperforms state-of-the-art open-source reward models across diverse STEM benchmarks. |
Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating large language models have been criticized for their complexity and instability. |
| Approach: | They propose a value-based calibration method to better align Large Language Models with human preferences. |
| Outcome: | The proposed method surpasses existing methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and diversity in different settings. |
CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models exhibit a specific cultural bias, neglecting values and differences of low-resource regions. |
| Approach: | They propose a culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. |
| Outcome: | The proposed model achieves state-of-the-art in cultural alignment and general reasoning. |
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual human preference data are difficult to obtain at scale, making it challenging to extend this framework to diverse languages. |
| Approach: | They propose a method where a reward model is trained on preference data in one source language and applied to other target languages. |
| Outcome: | The proposed approach is effective under comprehensive evaluation settings, including human evaluation. |
Reinforcement Learning for Large Language Models via Group Preference Reward Shaping (2025.emnlp-main)
Copied to clipboard
Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Zhimeng Guo, Shijie Zhou, Shuyue Hu, Vasant G. Honavar
| Challenge: | Existing methods for fine-tuning Large Language Models (LLMs) are expensive and sensitive to reward model quality. |
| Approach: | They propose a method that leverages preference-based comparisons rather than precise numerical rewards. |
| Outcome: | Experiments show that GPRS outperforms critic-model-free RL algorithms on RLHF and reasoning tasks. |
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. |