Sample-efficient LLM Optimization with Reset Replay

• URL: http://arxiv.org/abs/2508.06412v2
• Date: Thu, 14 Aug 2025 14:59:51 GMT
• Title: Sample-efficient LLM Optimization with Reset Replay
• Authors: Zichuan Liu, Jinyu Wang, Lei Song, Jiang Bian,
• Abstract summary: We introduce Reset Replay (LoRR), a plugin designed to enhance sample efficiency in any preference-based optimization framework.<n>LoRR incorporates a periodic reset strategy with reusing initial data, which preserves network plasticity.<n>Our experiments demonstrate that LoRR significantly boosts the performance of various preference optimization methods on both mathematical and general reasoning benchmarks.
• Score: 13.739451157239756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in post-training Large Language Models (LLMs), particularly through Reinforcement Learning (RL) and preference optimization methods, are key drivers for enhancing their reasoning capabilities. However, these methods are often plagued by low sample efficiency and a susceptibility to primacy bias, where overfitting to initial experiences degrades policy quality and damages the learning process. To address these challenges, we introduce LLM optimization with Reset Replay (LoRR), a general and powerful plugin designed to enhance sample efficiency in any preference-based optimization framework. LoRR core mechanism enables training at a high replay number, maximizing the utility of each collected data batch. To counteract the risk of overfitting inherent in high-replay training, LoRR incorporates a periodic reset strategy with reusing initial data, which preserves network plasticity. Furthermore, it leverages a hybrid optimization objective, combining supervised fine-tuning (SFT) and preference-based losses to further bolster data exploitation. Our extensive experiments demonstrate that LoRR significantly boosts the performance of various preference optimization methods on both mathematical and general reasoning benchmarks. Notably, an iterative DPO approach augmented with LoRR achieves comparable performance on challenging math tasks, outperforming some complex and computationally intensive RL-based algorithms. These findings highlight that LoRR offers a practical, sample-efficient, and highly effective paradigm for LLM finetuning, unlocking greater performance from limited data.

Related papers

• MiniRec: Data-Efficient Reinforcement Learning for LLM-based Recommendation [50.417769112326546]
  MiniRec is a data selection framework tailored for RL-based large language models (LLMs) recommendation.<n>It evaluates sample learnability using key RL signals -- rewards -- pruning samples that are too easy (too high reward) or too difficult (consistently low reward)
  arXiv  Detail & Related papers  (2026-02-04T07:15:49Z)
• LLM Optimization Unlocks Real-Time Pairwise Reranking [6.0141312590967635]
  Pairwise Reranking Prompting (PRP) has emerged as a promising plug-and-play approach due to its usability and effectiveness.<n>This paper presents a focused study on pairwise reranking, demonstrating that carefully applied optimization methods can significantly mitigate these issues.<n>We achieve a remarkable latency reduction of up to 166 times, from 61.36 seconds to 0.37 seconds per query, with an insignificant drop in performance measured by Recall@k.
  arXiv  Detail & Related papers  (2025-11-10T19:04:41Z)
• Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval [28.986143611245836]
  This paper introduces Retrv-R1, the first R1-style MLLM specifically designed for multimodal universal retrieval.<n>We find that directly applying the methods of DeepSeek-R1 to retrieval tasks is not feasible.<n>To address these issues, Retrv-R1 introduces an information compression module with a details inspection mechanism.
  arXiv  Detail & Related papers  (2025-10-03T06:16:58Z)
• 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)
• Filtering Learning Histories Enhances In-Context Reinforcement Learning [12.697029805927398]
  Transformer models (TMs) have exhibited remarkable in-context reinforcement learning capabilities.<n>We propose a simple yet effective approach, learning history filtering (LHF) to enhance ICRL.<n>LHF is the first approach to avoid source suboptimality by dataset preprocessing.
  arXiv  Detail & Related papers  (2025-05-21T06:00:41Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task.<n>Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively.<n>We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit [46.37267466656765]
  This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture.<n>Our experiments demonstrate how this architecture effectively decreases time without sacrificing the accuracy needed for reliable recommendation delivery.
  arXiv  Detail & Related papers  (2025-01-04T03:26:46Z)
• Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization [22.67700436936984]
  We introduce Direct Advantage Policy Optimization (DAPO), a novel step-level offline reinforcement learning algorithm.<n>DAPO employs a critic function to predict the reasoning accuracy at each step, thereby generating dense signals to refine the generation strategy.<n>Our results show that DAPO can effectively enhance the mathematical and code capabilities on both SFT models and RL models, demonstrating the effectiveness of DAPO.
  arXiv  Detail & Related papers  (2024-12-24T08:39:35Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)

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.