---
title: "少复制多依据：通过证据感知强化学习克服长上下文推理中的重复复制"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.19345v1"
permalink: "https://feed.astralor.com/items/itm_d72529776569c2e45570e4e9"
published: "2026-07-21T17:59:21.000Z"
score: 79
channel: "ai"
tags: ["大语言模型","强化学习","证据感知奖励","长上下文"]
---

# 少复制多依据：通过证据感知强化学习克服长上下文推理中的重复复制

## AI 点评

> 这篇论文值得每位关注长上下文LLM的研究者和工程师一读，它揭露了一个被我之前忽视但很致命的现象——模型在偷懒复制而非真正推理。GEAR方法轻量且可自动化，特别适合部署时希望控制推理成本同时提升正确率的团队。

## 速览

本文发现长上下文大语言模型在推理时普遍存在重复复制输入文本的问题，且随上下文长度加剧。通过将提示区分为关键证据和干扰上下文，表明根因是模型对关键证据聚焦不足。为此提出GEAR方法，通过证据重叠奖励和干扰惩罚来增强强化学习训练，在多个模型和基准上平均提升4.6分，尤其在长上下文中效果显著，同时减少了复制和思考长度。

## 关键点

- 识别出长上下文LLM的重复复制失败模式，并证实其随上下文长度加剧。
- 根因是模型对关键证据的聚焦不足，导致从提示中不加选择地复制。
- 提出GEAR方法，结合准确性、关键证据重叠奖励和干扰上下文惩罚。
- 在多尺度模型和基准上验证，平均提升+4.6点，长上下文提升更大。

## 全文

Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier. However, we identify a critical failure mode in this regime: \emph{repetitive copying}, where models extensively copy text from the input into their reasoning traces rather than productively solving the problem. We show that this behavior is pervasive across frontier long-context LLMs and intensifies with context length. By separating each prompt into task-relevant key evidence and irrelevant distractor context, we further show that the root cause is insufficient grounding: models copy from the prompt indiscriminately, and those that fail to focus on key evidence are far more likely to answer incorrectly. Motivated by this diagnosis, we propose GEAR (Grounding Evidence-Aware Reward), a reward shaping method that augments the accuracy signal with a grounding reward for overlap with key evidence and a distractor penalty for overlap with irrelevant context. To enable GEAR on natural-language data, we develop an automated pipeline that constructs evidence-annotated training data from arbitrary documents. We validate GEAR across multiple model scales and benchmarks, showing consistent improvements of up to +4.6 average points over standard RL with accuracy-based rewards, with larger gains at longer contexts, while also reducing repetitive copying and thinking length. Our findings suggest that, even as long-context evaluation shifts from simple retrieval toward complex reasoning, accurate grounding in relevant evidence remains an indispensable capability with substantial room for improvement.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d72529776569c2e45570e4e9