# Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes

arXiv: https://arxiv.org/abs/2301.01751 · HTML: https://mlsanity.com/paper/2301.01751/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 43 of its 55 references that are in the map.
- First posted on arXiv 4 Jan 2023.

## Placed in

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

## Builds on (most cited first, 30 of 43)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://mlsanity.com/paper/2203.06566/) (2022)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [Language Model Cascades](https://mlsanity.com/paper/2207.10342/) (2022)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [NILE : Natural Language Inference with Faithful Natural Language Explanations](https://mlsanity.com/paper/2005.12116/) (2020)
- [Compositional Semantic Parsing with Large Language Models](https://mlsanity.com/paper/2209.15003/) (2022)

## Built on by (most cited first, 15 of 15)

- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence](https://mlsanity.com/paper/2306.07075/) (2023)
- [Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows](https://mlsanity.com/paper/2312.11681/) (2023)
- [SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration](https://mlsanity.com/paper/2412.12151/) (2024)
- [Large Language Model Programs](https://mlsanity.com/paper/2305.05364/) (2023)
- [Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information](https://mlsanity.com/paper/2408.10615/) (2024)
- [KwaiYiiMath: Technical Report](https://mlsanity.com/paper/2310.07488/) (2023)
- [DTCRS: Dynamic Tree Construction for Recursive Summarization](https://mlsanity.com/paper/2604.07012/) (2026)
- [AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement](https://mlsanity.com/paper/2502.02067/) (2025)
- [How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning](https://mlsanity.com/paper/2605.23023/) (2026)
- [DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction](https://mlsanity.com/paper/2509.14507/) (2025)
- [Robust Native Language Identification through Agentic Decomposition](https://mlsanity.com/paper/2509.16666/) (2025)
- [Dynamic Template Selection for Output Token Generation Optimization: MLP-Based and Transformer Approaches](https://mlsanity.com/paper/2511.20683/) (2025)
- [A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building](https://mlsanity.com/paper/2512.01434/) (2025)

## Abstract (arXiv)

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow support and infrastructure to remain competitive. We describe iterated decomposition, a human-in-the-loop workflow for developing and refining compositional LM programs. We improve the performance of compositions by zooming in on failing components and refining them through decomposition, additional context, chain of thought, etc. To support this workflow, we develop ICE, an open-source tool for visualizing the execution traces of LM programs. We apply iterated decomposition to three real-world tasks and improve the accuracy of LM programs over less compositional baselines: describing the placebo used in a randomized controlled trial (25% to 65%), evaluating participant adherence to a medical intervention (53% to 70%), and answering NLP questions on the Qasper dataset (38% to 69%). These applications serve as case studies for a workflow that, if automated, could keep ML systems interpretable and safe even as they scale to increasingly complex tasks.