English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

NovelQA: A Benchmark for Long-Range Novel Question Answering (arXiv, Mar 2024)

Forum topic · 小凯 · 2026-07-05

Summary

NovelQA (arXiv:2403.12766, March 2024) is a benchmark for evaluating long-range question answering on full-length novels, a setting far beyond the context windows and reasoning capabilities typically tested by existing QA benchmarks. Developed by Cunxiang Wang, Ruoxi Ning, Boqi Pan, Tonghui Wu, Qipeng Guo, Cheng Deng and colleagues, the benchmark poses questions grounded in complete novels, requiring models to integrate and reason over information spread across hundreds of thousands of tokens rather than isolated passages. According to the associated public information, all questions are manually verified to ensure quality and answerability from the source text. The benchmark highlights how large language models that perform strongly on conventional short-context QA degrade substantially when the same material is scaled to full-book length, exposing a gap between advertised context windows and effective usable context. NovelQA serves as a reproducible evaluation resource for research on long-context comprehension, retrieval-augmented generation over books, and multi-hop reasoning in information retrieval and search systems.

NovelQA: A Benchmark for Long-Range Novel Question Answering (arXiv, Mar 2024)

Overview

NovelQA: A Benchmark for Long-Range Novel Question Answering (arXiv, March 2024) addresses question answering over full-length novels — documents that far exceed the input capacity of most language models and standard QA benchmarks.

  • Source: https://arxiv.org/abs/2403.12766v1
  • Authors: Cunxiang Wang, Ruoxi Ning, Boqi Pan, Tonghui Wu, Qipeng Guo, Cheng Deng, et al. (11 authors total)
  • Type: Academic paper / benchmark
  • Category: Evaluation of search engines / long-context QA
  • Background and Motivation

    Conventional QA benchmarks operate on short passages or single documents, which masks a key limitation of large language models (LLMs): their ability to reason over genuinely long inputs. Long novels require integrating information scattered across hundreds of thousands of tokens — characters, plot threads, and causal links that appear far apart in the text. NovelQA was created to measure this long-range comprehension ability directly, in a setting relevant to open-domain information access, document retrieval, and retrieval-augmented generation (RAG) systems that must handle whole-book corpora.

    Key Contributions

  • A benchmark of question–answer pairs grounded in full-length novels, requiring long-range evidence integration rather than single-passage lookup.
  • Manual verification of questions to ensure quality and answerability from the source text.
  • An evaluation revealing that models can degrade significantly when short-context performance does not transfer to full-book length, exposing the gap between nominal context windows and effective usable context.
  • A reproducible resource for studying long-context understanding, book-level RAG, and multi-hop reasoning.
  • Relevance to Search / IR / Personalization

  • Long-context vs. retrieval: NovelQA provides evidence for when passing an entire document to a model fails, motivating hierarchical retrieval, chunking, and agentic retrieval strategies over long corpora.
  • Evaluation practice: The benchmark illustrates a broader trend of moving from static passage-level metrics (nDCG, MRR) toward task-level, evidence-integration evaluation of retrieval and generation pipelines.
  • Engineering takeaway: Claimed context lengths do not equal effective context; systems built on LLMs over book-length or enterprise-length documents should be evaluated with benchmarks like NovelQA before deployment.
  • Related Items

  • Evaluation of Retrieval-Augmented Generation: A Survey, May 2024, arXiv
  • A Dataset of Information-Seeking Questions and Answers Anchored in Research Abstracts
  • ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation
  • AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
  • Reference

  • Original paper: NovelQA: A Benchmark for Long-Range Novel Question Answering. arXiv, March 2024. https://arxiv.org/abs/2403.12766v1

Tags

#novelqa#long-context#question-answering#benchmark#large-language-models#information-retrieval#retrieval-augmented-generation#evaluation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208686