Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization

• URL: http://arxiv.org/abs/2508.13993v1
• Date: Tue, 19 Aug 2025 16:33:55 GMT
• Title: Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
• Abstract summary: LongMab-PO is a novel framework that generates high-quality and diverse responses for long-context modeling tasks.<n> Experimental results show that LongMab-PO significantly improves the diversity and quality of preference data pairs.
• Score: 56.97588709890706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have explored fine-tuning Large Language Models (LLMs) with synthetic data to enhance their long-context capabilities. However, the effectiveness of such approaches is often limited by the low diversity and factual inconsistencies in the generated data. To address these challenges, we propose LongMab-PO, a novel framework that leverages a Multi-Armed Bandit (MAB) rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses and constructing preference data pairs for Direct Preference Optimization (DPO) training. Specifically, we treat context chunks as arms of MAB, select chunks based on their expected reward scores to input into LLMs to generate responses, and iteratively update these scores based on reward feedback. This exploration and exploitation process enables the model to focus on the most relevant context segments, thereby generating and collecting high-quality and diverse responses. Finally, we collect these generated responses from the rollout process and apply the DPO method to further optimize the LLM. Experimental results show that LongMab-PO significantly improves the diversity and quality of preference data pairs, achieving state-of-the-art performance on long-context reasoning benchmarks. All code and data will be released on https://github.com/NEUIR/LongMab-PO.

Related papers

• Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation [0.0]
  This work introduces a modular framework for synthetic long-context data generation via prompt-based interaction with large language models (LLMs)<n>The framework supports multiple training and alignment objectives, including Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO)<n>It encompasses four core generation paradigms: multi-turn conversational dialogues, document-grounded input-output pairs, verifiable instruction-response tasks, and long-context reasoning examples.
  arXiv  Detail & Related papers  (2025-09-01T07:08:45Z)
• Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization [5.856976164399712]
  We present a hybrid method that combines retrieval-augmented systems with long-context windows supported by recent language models.<n>Our results on the multi-document summarization task showcase the effectiveness of our method across model classes and sizes.
  arXiv  Detail & Related papers  (2025-04-17T14:24:51Z)
• WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale [86.25450054683172]
  WildLong extracts meta-information from real user queries to produce scalable data.<n>It supports multi-document reasoning, such as cross-document comparison and aggregation.<n>It surpasses existing open-source long-context-optimized models across benchmarks.
  arXiv  Detail & Related papers  (2025-02-23T18:59:09Z)
• Does RAG Really Perform Bad For Long-Context Processing? [15.889864680212147]
  RetroLM is a novel framework for long-context processing.<n>Unlike traditional methods, RetroLM employs KV-level retrieval augmentation.<n>Building on this framework, we develop a specialized retriever for precise retrieval of critical pages.
  arXiv  Detail & Related papers  (2025-02-17T05:02:25Z)
• LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information [76.26257306813899]
  Long-form generation is crucial for academic writing papers and repo-level code generation.<n>Existing methods that utilize preference learning with outcome supervision often fail to provide detailed feedback for extended contexts.<n>We propose enhancing long-form generation by incorporating process supervision.
  arXiv  Detail & Related papers  (2025-02-04T08:25:17Z)
• GATEAU: Selecting Influential Samples for Long Context Alignment [62.87020831987625]
  GATEAU identifies influential samples enriched with long-range dependency relations.<n>Model trained on selected samples exhibits better instruction-following and long-context understanding capabilities.
  arXiv  Detail & Related papers  (2024-10-21T04:30:53Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios.<n>Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement.<n>We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent.<n>Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models [0.8399688944263842]
  Large Language Models (LLMs) have the capability to understand and generate human-like text from input queries. This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines. We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding.
  arXiv  Detail & Related papers  (2024-06-17T04:35:17Z)
• Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models [13.091271774417867]
  Long-context modeling capabilities are important for large language models (LLMs) in various applications. We propose a data mining framework textbfProLong that can assign each training sample with a long dependency score. Comprehensive experiments on multiple benchmarks indicate that ProLong effectively identifies documents that carry long dependencies.
  arXiv  Detail & Related papers  (2024-05-28T07:36:56Z)
• Long Context Alignment with Short Instructions and Synthesized Positions [56.1267385315404]
  This paper introduces Step-Skipping Alignment (SkipAlign) It is a new technique designed to enhance the long-context capabilities of Large Language Models (LLMs) With a careful selection of the base model and alignment datasets, SkipAlign with only 6B parameters achieves it's best performance and comparable with strong baselines like GPT-3.5-Turbo-16K on LongBench.
  arXiv  Detail & Related papers  (2024-05-07T01:56:22Z)
• Effective Long-Context Scaling of Foundation Models [90.57254298730923]
  We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2.
  arXiv  Detail & Related papers  (2023-09-27T21:41:49Z)

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.