# NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts

arXiv: https://arxiv.org/abs/2506.02000 · HTML: https://mlsanity.com/paper/2506.02000/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [Retrieval meets Long Context Large Language Models](https://mlsanity.com/paper/2310.03025/) (2023)
- [LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K](https://mlsanity.com/paper/2402.05136/) (2024)
- [One Thousand and One Pairs: A "novel" challenge for long-context language models](https://mlsanity.com/paper/2406.16264/) (2024)
- [NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities](https://mlsanity.com/paper/2407.11963/) (2024)
- [NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens](https://mlsanity.com/paper/2403.12766/) (2024)
- [FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models](https://mlsanity.com/paper/2402.14116/) (2024)
- [Making Long-Context Language Models Better Multi-Hop Reasoners](https://mlsanity.com/paper/2408.03246/) (2024)
- [AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark](https://mlsanity.com/paper/2408.14845/) (2024)
- [Marathon: A Race Through the Realm of Long Context with Large Language Models](https://mlsanity.com/paper/2312.09542/) (2023)
- [EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models](https://mlsanity.com/paper/2504.07100/) (2025)

## Built on by (most cited first, 8 of 8)

- [DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections](https://mlsanity.com/paper/2508.15851/) (2025)
- [When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering](https://mlsanity.com/paper/2601.19827/) (2026)
- [The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training](https://mlsanity.com/paper/2602.09448/) (2026)
- [Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation](https://mlsanity.com/paper/2604.18169/) (2026)
- [MiA-Signature: Approximating Global Activation for Long-Context Understanding](https://mlsanity.com/paper/2605.06416/) (2026)
- [Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning](https://mlsanity.com/paper/2606.18831/) (2026)
- [RECON: Benchmarking Agent Memory for Compositional Reasoning over Long Contexts](https://mlsanity.com/paper/2607.16716/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

Current large language models (LLMs) struggle to answer questions that span tens of thousands of tokens, especially when multi-hop reasoning is involved. While prior benchmarks explore long-context comprehension or multi-hop reasoning in isolation, none jointly vary context length and reasoning depth in natural narrative settings. We introduce NovelHopQA, the first benchmark to evaluate 1-4 hop QA over 64k-128k-token excerpts from 83 full-length public-domain novels. A keyword-guided pipeline builds hop-separated chains grounded in coherent storylines. We evaluate seven state-of-the-art models and apply oracle-context filtering to ensure all questions are genuinely answerable. Human annotators validate both alignment and hop depth. We additionally present retrieval-augmented generation (RAG) evaluations to test model performance when only selected passages are provided instead of the full context. We noticed consistent accuracy drops with increased hops and context length increase, even for frontier models-revealing that sheer scale does not guarantee robust reasoning. Failure-mode analysis highlights common breakdowns such as missed final-hop integration and long-range drift. NovelHopQA offers a controlled diagnostic setting to test multi-hop reasoning at scale. All code and datasets are available at https://novelhopqa.github.io.