# REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing

arXiv: https://arxiv.org/abs/2609.36984 · HTML: https://mlsanity.com/paper/2609.36984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 34 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 32)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [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)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control](https://mlsanity.com/paper/1910.13294/) (2019)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA](https://mlsanity.com/paper/1906.07132/) (2019)
- [Understanding Dataset Design Choices for Multi-hop Reasoning](https://mlsanity.com/paper/1904.12106/) (2019)
- [MoreHopQA: More Than Multi-hop Reasoning](https://mlsanity.com/paper/2406.13397/) (2024)
- [LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts](https://mlsanity.com/paper/2510.19363/) (2025)
- [Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?](https://mlsanity.com/paper/2409.05197/) (2024)
- [Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training](https://mlsanity.com/paper/2607.28109/) (2026)

## Abstract (arXiv)

Complex questions often require multi-hop reasoning that connects facts distributed across sources or distant regions of a long context through intermediate steps. Benchmarks commonly evaluate this ability with questions built around predefined reasoning chains, treating a correct answer as evidence that the intended composition was used. Yet answer correctness alone leaves open whether success depends on the evidence associated with each intended step: models may instead rely on memorized associations, shorter paths, or partial evidence. We examine this dependence using the Behavioral Necessity Rate (BNR), which measures how often targeted evidence removal prevents answer recovery on initially correct instances. Across five existing benchmarks, panel-mean BNR ranges from 16.6% to 48.9%, exposing a substantial gap between annotated structure and observed dependence. Guided by this diagnosis, we introduce REALHOP, a diagnose-construct-verify framework that rebinds entities, factorizes selected relations, adds complete competing paths, and places evidence at traceable locations. Structural and semantic checks precede freezing; behavioral interventions follow. On 790 paired MuSiQue questions, REALHOP raises panel-mean BNR from 27.4% to 94.4% while retaining high Full accuracy. It also yields high BNR on REALHOP-FRAMES and REALHOP-LONGBENCH. On 216 long-context questions, the matched multiple-choice spread across 16 models grows from 13.9 to 59.2 points and persists under repeated open-ended evaluation. Together, these results show that a conceptually coherent chain and a correct final answer do not by themselves establish multi-hop reasoning. Verifying that success depends on every intended hop is therefore as fundamental to multi-hop evaluation as measuring answer accuracy itself.