# GenDec: A robust generative Question-decomposition method for Multi-hop reasoning

arXiv: https://arxiv.org/abs/2402.11166 · HTML: https://mlsanity.com/paper/2402.11166/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 52 references that are in the map.
- First posted on arXiv 17 Feb 2024.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Tab-CoT: Zero-shot Tabular Chain of Thought](https://mlsanity.com/paper/2305.17812/) (2023)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?](https://mlsanity.com/paper/2002.09919/) (2020)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering](https://mlsanity.com/paper/2208.10297/) (2022)
- [Prompt-based Conservation Learning for Multi-hop Question Answering](https://mlsanity.com/paper/2209.06923/) (2022)

## Built on by (most cited first, 13 of 13)

- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models](https://mlsanity.com/paper/2402.14116/) (2024)
- [MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning](https://mlsanity.com/paper/2510.13614/) (2025)
- [ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering](https://mlsanity.com/paper/2506.00232/) (2025)
- [Question Decomposition for Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.00355/) (2025)
- [POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval](https://mlsanity.com/paper/2505.19189/) (2025)
- [DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.17212/) (2026)
- [Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning](https://mlsanity.com/paper/2508.19113/) (2025)
- [Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability](https://mlsanity.com/paper/2412.15101/) (2024)
- [Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks](https://mlsanity.com/paper/2501.06286/) (2025)
- [PARSE: An Open-Domain Reasoning Question Answering Benchmark for Persian](https://mlsanity.com/paper/2602.01246/) (2026)
- [Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"](https://mlsanity.com/paper/2602.04853/) (2026)
- [Knowledge Dependency Estimation for Reliable Question Answering](https://mlsanity.com/paper/2605.28047/) (2026)

## Abstract (arXiv)

Multi-hop QA (MHQA) involves step-by-step reasoning to answer complex questions and find multiple relevant supporting facts. However, Existing large language models'(LLMs) reasoning ability in multi-hop question answering remains exploration, which is inadequate in answering multi-hop questions. Moreover, it is unclear whether LLMs follow a desired reasoning chain to reach the right final answer. In this paper, we propose a generative question decomposition method (GenDec) from the perspective of explainable QA by generating independent and complete sub-questions based on incorporating additional extracted evidence for enhancing LLMs' reasoning ability in RAG. To demonstrate the impact, generalization, and robustness of Gendec, we conduct two experiments, the first is combining GenDec with small QA systems on paragraph retrieval and QA tasks. We secondly examine the reasoning capabilities of various state-of-the-art LLMs including GPT-4 and GPT-3.5 combined with GenDec. We experiment on the HotpotQA, 2WikihopMultiHopQA, MuSiQue, and PokeMQA datasets.