arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.02465cs.CL
收藏

DetectiveQA:评估侦探小说上的长上下文推理

DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels

School of Computer Science, Fudan University(复旦大学计算机科学学院);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Shanghai AI Laboratory(上海人工智能实验室)

Zhe Xu, Jiasheng Ye, Xiaoran Liu, Xiangyang Liu, Tianxiang Sun, Zhigeng Liu, Qipeng Guo, Linlin Li, Qun Liu, Xuanjing Huang, Xipeng Qiu

AI总结:

本文提出 DetectiveQA 数据集与逐步推理指标,利用超10万 token 的侦探小说和1200道中英双语标注题评估主流 LLM,揭示其长上下文推理与证据检索仍面临挑战。

摘要:

近来,大量努力被投入于提升大型语言模型(LLM)的长上下文能力,尤其是长上下文推理。为促进该研究,我们提出 DetectiveQA,这是一个专为长上下文中的叙事推理设计的数据集。我们利用平均超过10万 token 的侦探小说,构建了一个包含1200道人工标注问题的数据集,问题以中文和英文呈现,每道题均配有相应的参考推理步骤。此外,我们提出一种逐步推理指标,以增强对 LLM 推理过程的评估。我们验证了该方法,并评估了包括 GPT-4、Claude 和 LLaMA 在内的主流 LLM,结果揭示了持续存在的长上下文推理挑战,并证明它们在证据检索方面存在困难。我们的发现为长上下文推理研究提供了有价值的洞见,并为更严格的评估奠定基础。

英文摘要:

Recently, significant efforts have been devoted to enhancing the long-context capabilities of Large Language Models (LLMs), particularly in long-context reasoning. To facilitate this research, we propose \textbf{DetectiveQA}, a dataset specifically designed for narrative reasoning within long contexts. We leverage detective novels, averaging over 100k tokens, to create a dataset containing 1200 human-annotated questions in both Chinese and English, each paired with corresponding reference reasoning steps. Furthermore, we introduce a step-wise reasoning metric, which enhances the evaluation of LLMs' reasoning processes. We validate our approach and evaluate the mainstream LLMs, including GPT-4, Claude, and LLaMA, revealing persistent long-context reasoning challenges and demonstrating their evidence-retrieval challenges. Our findings offer valuable insights into the study of long-context reasoning and lay the base for more rigorous evaluations.

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。

↑