# Is a Question Decomposition Unit All We Need?

arXiv: https://arxiv.org/abs/2205.12538 · HTML: https://mlsanity.com/paper/2205.12538/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks](https://mlsanity.com/paper/2204.05660/) (2022)
- [Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://mlsanity.com/paper/2009.00751/) (2020)
- [Less is More: Summary of Long Instructions is Better for Program Synthesis](https://mlsanity.com/paper/2203.08597/) (2022)
- [How Many Data Samples is an Additional Instruction Worth?](https://mlsanity.com/paper/2203.09161/) (2022)
- [Neural Compositional Denotational Semantics for Question Answering](https://mlsanity.com/paper/1808.09942/) (2018)
- [Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering](https://mlsanity.com/paper/2203.07522/) (2022)
- [Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes](https://mlsanity.com/paper/2204.07693/) (2022)

## Built on by (most cited first, 30 of 37)

- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://mlsanity.com/paper/2402.03620/) (2024)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2404.15522/) (2024)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning](https://mlsanity.com/paper/2501.06590/) (2025)
- [MoreHopQA: More Than Multi-hop Reasoning](https://mlsanity.com/paper/2406.13397/) (2024)
- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [Instruction Tuned Models are Quick Learners](https://mlsanity.com/paper/2306.05539/) (2023)
- [Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models](https://mlsanity.com/paper/2502.15964/) (2025)
- [Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration](https://mlsanity.com/paper/2504.04915/) (2025)
- [HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models](https://mlsanity.com/paper/2208.08232/) (2022)
- [InstructExcel: A Benchmark for Natural Language Instruction in Excel](https://mlsanity.com/paper/2310.14495/) (2023)
- [Exploring Question Decomposition for Zero-Shot VQA](https://mlsanity.com/paper/2310.17050/) (2023)
- [Large Language Model Programs](https://mlsanity.com/paper/2305.05364/) (2023)
- [Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation](https://mlsanity.com/paper/2410.20753/) (2024)
- [SQLucid: Grounding Natural Language Database Queries with Interactive Explanations](https://mlsanity.com/paper/2409.06178/) (2024)
- [Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs](https://mlsanity.com/paper/2405.12933/) (2024)
- [Visual Question Decomposition on Multimodal Large Language Models](https://mlsanity.com/paper/2409.19339/) (2024)
- [Fast-Slow-Thinking: Complex Task Solving with Large Language Models](https://mlsanity.com/paper/2504.08690/) (2025)
- [DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models](https://mlsanity.com/paper/2310.05074/) (2023)
- [FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline](https://mlsanity.com/paper/2410.13959/) (2024)
- [PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving](https://mlsanity.com/paper/2507.07495/) (2025)
- [In-Context Ability Transfer for Question Decomposition in Complex QA](https://mlsanity.com/paper/2310.18371/) (2023)
- [GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?](https://mlsanity.com/paper/2407.10245/) (2024)

## Abstract (arXiv)

Large Language Models (LMs) have achieved state-of-the-art performance on many Natural Language Processing (NLP) benchmarks. With the growing number of new benchmarks, we build bigger and more complex LMs. However, building new LMs may not be an ideal option owing to the cost, time and environmental impact associated with it. We explore an alternative route: can we modify data by expressing it in terms of the model's strengths, so that a question becomes easier for models to answer? We investigate if humans can decompose a hard question into a set of simpler questions that are relatively easier for models to solve. We analyze a range of datasets involving various forms of reasoning and find that it is indeed possible to significantly improve model performance (24% for GPT3 and 29% for RoBERTa-SQuAD along with a symbolic calculator) via decomposition. Our approach provides a viable option to involve people in NLP research in a meaningful way. Our findings indicate that Human-in-the-loop Question Decomposition (HQD) can potentially provide an alternate path to building large LMs. Code and data is available at https://github.com/Pruthvi98/QuestionDecomposition