Group-Aware Reinforcement Learning for Output Diversity in Large Language Models (2025.emnlp-main)
Copied to clipboard
Oron Anschel, Alon Shoshan, Adam Botach, Shunit Haviv Hakimi, Asaf Gendler, Emanuel Ben Baruch, Nadav Bhonker, Igor Kviatkovsky, Manoj Aggarwal, Gerard Medioni
| Challenge: | Large Language Models suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist. |
| Approach: | They propose a group-aware policy optimization extension of GRPO that computes rewards over the group as a whole. |
| Outcome: | The proposed model improves on standard LLM benchmarks without compromising accuracy. |
Similar Papers
GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026.findings-acl)
Copied to clipboard
Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao
| Challenge: | Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, but in real-world code editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers. |
| Approach: | They propose a group-relative method that finds an interval with the highest SNR and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation. |
| Outcome: | The proposed method improves on nine instruction-tuned LLMs while remaining plug-and-play and efficient. |
GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization (2025.acl-long)
Copied to clipboard
Zhouhong Gu, Xingzhou Chen, Xiaoran Shi, Tao Wang, Suhang Zheng, Tianyu Li, Hongwei Feng, Yanghua Xiao
| Challenge: | Existing methods for achieving this require a limited understanding of constraints and can be hallucinating or brittle. |
| Approach: | They propose a framework that combines adversarial training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints. |
| Outcome: | Extensive experiments show that GAPO significantly outperforms existing methods like PPO, DPO, and KTO in fine-grained constraints. |
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs . |
| Approach: | They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals . |
| Outcome: | The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks. |
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. |
| Approach: | They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives. |
| Outcome: | The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs. |
Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)
Copied to clipboard
| Challenge: | Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations. |
| Approach: | They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning. |
| Outcome: | The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance. |
BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent preference-based fine-tuning methods have limited exploration in offline training . previous methods have been limited by the lack of exploration inherent in offline learning . |
| Approach: | They propose a method that normalizes rewards across a group of completed tasks to mitigate social bias in Large Language Models. |
| Outcome: | The proposed approach outperforms DPO and PPO in multiple benchmarks . it can overcome limitations of previous preference-based methods . |
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang
| Challenge: | Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). |
| Approach: | a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance. |
| Outcome: | a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models . |
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. |
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning (2026.findings-acl)
Copied to clipboard
Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi
| Challenge: | Existing methods for group-relative policy optimization rely on scalar correctness rewards that are often non-injective with respect to semantic content. |
| Approach: | They propose a framework that calibrates the reward signal using the semantic density of sampled groups. |
| Outcome: | The proposed framework outperforms strong baselines on five math benchmarks with 7,000 samples and 55 cost. |
End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multi-agent reinforcement learning methods depend on large critic networks to evaluate joint actions, leading to instability and high memory costs. |
| Approach: | They propose a method to optimize large language models for agent-specific roles . they propose combining agent-based frameworks with retrieval-augmented generation . |
| Outcome: | Experiments show that multi-agent group policy optimization outperforms baselines in task performance and computational efficiency. |