Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

• URL: http://arxiv.org/abs/2505.12929v1
• Date: Mon, 19 May 2025 10:14:08 GMT
• Title: Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
• Authors: Zhihe Yang, Xufang Luo, Zilong Wang, Dongqi Han, Zhiyuan He, Dongsheng Li, Yunjian Xu,
• Abstract summary: Low-probability tokens disproportionately influence model updates due to their large gradient magnitudes.<n>We propose two novel methods: Advantage Reweighting and Low-Probability Token Isolation (Lopti)<n>Our approaches promote balanced updates across tokens with varying probabilities, thereby enhancing the efficiency ofReinforcement learning.
• Score: 25.575582861331405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy Optimization (GRPO) demonstrating exceptional effectiveness. In this study, we identify a critical yet underexplored issue in RL training: low-probability tokens disproportionately influence model updates due to their large gradient magnitudes. This dominance hinders the effective learning of high-probability tokens, whose gradients are essential for LLMs' performance but are substantially suppressed. To mitigate this interference, we propose two novel methods: Advantage Reweighting and Low-Probability Token Isolation (Lopti), both of which effectively attenuate gradients from low-probability tokens while emphasizing parameter updates driven by high-probability tokens. Our approaches promote balanced updates across tokens with varying probabilities, thereby enhancing the efficiency of RL training. Experimental results demonstrate that they substantially improve the performance of GRPO-trained LLMs, achieving up to a 46.2% improvement in K&K Logic Puzzle reasoning tasks. Our implementation is available at https://github.com/zhyang2226/AR-Lopti.

Related papers

• Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle [53.239242017802056]
  Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM)<n>However, current RL pipelines often suffer from training inefficiencies caused by two underexplored issues: Advantage Collapsing and Rollout Silencing.<n>We propose Shuffle-R1, a simple yet principled framework that improves RL fine-tuning efficiency by dynamically restructuring trajectory sampling and batch composition.
  arXiv  Detail & Related papers  (2025-08-07T17:53:47Z)
• Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning [106.68304931854038]
  Reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs)<n>We conduct a systematic empirical analysis of the entropy-performance exchange mechanism of RLVR across different levels of granularity.<n>Our analysis reveals that, in the rising stage, entropy reduction in negative samples facilitates the learning of effective reasoning patterns.<n>In the plateau stage, learning efficiency strongly correlates with high-entropy tokens present in low-perplexity samples and those located at the end of sequences.
  arXiv  Detail & Related papers  (2025-08-04T10:08:10Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [82.43575191712726]
  We introduce a fine-grained analytic framework to dissect the impact ofReinforcement learning on reasoning.<n>Our framework specifically investigates key elements that have been hypothesized to benefit from RL training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models [63.98194996746229]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• Behavior Injection: Preparing Language Models for Reinforcement Learning [24.46625106928253]
  Reinforcement fine-tuning (RFT) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs)<n>LLMs can respond very inconsistently to RFT: some show substantial performance gains, while others plateau or even degrade.<n>We propose behavior injection, a task-agnostic data-augmentation scheme applied prior to RL.
  arXiv  Detail & Related papers  (2025-05-25T00:54:50Z)
• Bridging Supervised Learning and Reinforcement Learning in Math Reasoning [55.889740979706815]
  Reinforcement Learning (RL) has played a central role in the recent surge of math abilities by enabling self-improvement through binary verifier signals.<n>In this work, we propose Negative-aware Fine-Tuning (NFT) -- a supervised approach that enables LLMs to reflect on their failures and improve autonomously with no external teachers.
  arXiv  Detail & Related papers  (2025-05-23T17:17:40Z)
• Effective Reinforcement Learning for Reasoning in Language Models [30.994610715391776]
  Reinforcement learning (RL) has emerged as a promising strategy for improving the reasoning capabilities of language models (LMs) in domains such as mathematics and coding.<n>We analyze RL algorithm design decisions for LM reasoning, focusing on relatively small models due to computational constraints.<n>Our findings are: (i) on-policy RL significantly outperforms supervised fine-tuning (SFT), (ii) PPO-based off-policy updates increase accuracy instead of reduce variance, and (iii) removing KL divergence can lead to more concise generations and higher accuracy.
  arXiv  Detail & Related papers  (2025-05-22T18:48:09Z)
• Token-Efficient RL for LLM Reasoning [0.02488650627593658]
  We propose reinforcement learning strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits.<n>Building on early policy gradient methods with baseline subtraction, we design critic-free methods that operate on a small, informative subset of output tokens.<n>We show that our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication.
  arXiv  Detail & Related papers  (2025-04-29T14:58:43Z)
• Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning [4.325768677318839]
  We propose Adaptive Group Policy Optimization (AGPO) which contains two simple but effective modifications.<n>The experiments demonstrate our methods achieve more stable training and comparable or superior performance with significantly fewer tokens in reasoning steps.
  arXiv  Detail & Related papers  (2025-03-20T08:48:57Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes.<n>We present a novel framework for identifying these tokens through rollout sampling.<n>We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding [11.470005425117371]
  We propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) Our method aims to adeptly capture nuanced label-sensitive semantic features during RL, thereby enhancing natural language understanding. Experiments conducted on five diverse foundation models across eight tasks showcase promising results.
  arXiv  Detail & Related papers  (2024-05-30T07:19:31Z)
• Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales [13.818149654692863]
  Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. In this work, we improve the stability of RL training by adapting the reverse cross entropy (RCE) from supervised learning for noisy data to define a symmetric RL loss.
  arXiv  Detail & Related papers  (2024-05-27T19:28:33Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)
• Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning [92.18524491615548]
  Contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL) We study how RL can be empowered by contrastive learning in a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank transitions. Under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs.
  arXiv  Detail & Related papers  (2022-07-29T17:29:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.