DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels

TL;DR

DetectiveQA is a novel dataset designed to evaluate long-context reasoning in large language models using detective novels, highlighting ongoing challenges in reasoning and evidence retrieval.

Contribution

The paper introduces DetectiveQA, a new dataset with annotated questions and reasoning steps for narrative reasoning in long texts, and proposes a step-wise reasoning metric for evaluation.

Findings

LLMs show persistent long-context reasoning challenges

Evidence retrieval remains difficult for mainstream LLMs

DetectiveQA provides a rigorous benchmark for future research

Abstract

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.