arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14550cs.CLcs.AI
收藏

GraphReader:构建基于图的智能体以增强大型语言模型的长上下文能力

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models

Alibaba Group(阿里巴巴集团);The Chinese University of Hong Kong(香港中文大学);Shanghai AI Laboratory(上海人工智能实验室);University of Manchester(曼彻斯特大学)

Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, Wenbo Su, Bo Zheng

AI总结:

GraphReader通过将长文本构建为图并让智能体自主探索,以4k上下文窗口在长上下文任务上大幅超越GPT-4-128k,并在单跳和多跳基准上表现优异。

摘要:

长上下文能力对于大型语言模型(LLMs)处理复杂且长输入的任务至关重要。尽管已有大量工作致力于优化LLMs以处理长上下文,但在稳健地处理长输入方面仍存在挑战。本文介绍了GraphReader,一个基于图的智能体系统,通过将长文本结构化为图,并利用智能体自主探索该图来处理长文本。在接收到问题后,智能体首先进行逐步分析并制定合理的计划。随后,它调用一组预定义的函数来读取节点内容和邻居信息,从而实现对图的从粗到细的探索。在整个探索过程中,智能体持续记录新见解并反思当前情况以优化过程,直到收集到足够的信息来生成答案。在LV-Eval数据集上的实验结果表明,使用4k上下文窗口的GraphReader,在16k到256k的上下文长度范围内,大幅且一致地优于GPT-4-128k。此外,我们的方法在四个具有挑战性的单跳和多跳基准测试上展现了优越的性能。

英文摘要:

Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, challenges persist in robustly processing long inputs. In this paper, we introduce GraphReader, a graph-based agent system designed to handle long texts by structuring them into a graph and employing an agent to explore this graph autonomously. Upon receiving a question, the agent first undertakes a step-by-step analysis and devises a rational plan. It then invokes a set of predefined functions to read node content and neighbors, facilitating a coarse-to-fine exploration of the graph. Throughout the exploration, the agent continuously records new insights and reflects on current circumstances to optimize the process until it has gathered sufficient information to generate an answer. Experimental results on the LV-Eval dataset reveal that GraphReader, using a 4k context window, consistently outperforms GPT-4-128k across context lengths from 16k to 256k by a large margin. Additionally, our approach demonstrates superior performance on four challenging single-hop and multi-hop benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑