# Reasoning Circuits: Few-shot Multihop Question Generation with Structured Rationales

arXiv: https://arxiv.org/abs/2211.08466 · HTML: https://mlsanity.com/paper/2211.08466/

## Key facts

- Cited by 3 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 7 of its 38 references that are in the map.
- First posted on arXiv 15 Nov 2022.

## Placed in

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

## Builds on (most cited first, 7 of 7)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Multi-hop Question Answering](https://mlsanity.com/paper/2204.09140/) (2022)
- [Stronger Transformers for Neural Multi-Hop Question Generation](https://mlsanity.com/paper/2010.11374/) (2020)

## Built on by (most cited first, 3 of 3)

- [What Has Been Lost with Synthetic Evaluation?](https://mlsanity.com/paper/2505.22830/) (2025)
- [ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions](https://mlsanity.com/paper/2312.01661/) (2023)
- [Automatic Generation of Inference Making Questions for Reading Comprehension Assessments](https://mlsanity.com/paper/2506.08260/) (2025)

## Abstract (arXiv)

Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages using several reasoning steps. Chain-of-thought rationale generation has been shown to improve performance on multi-step reasoning tasks and make model predictions more interpretable. However, few-shot performance gains from including rationales have been largely observed only in +100B language models, and otherwise require large scale manual rationale annotation. In this work, we introduce a new framework for applying chain-of-thought inspired structured rationale generation to multi-hop question generation under a very low supervision regime (8- to 128-shot). We propose to annotate a small number of examples following our proposed multi-step rationale schema, treating each reasoning step as a separate task to be performed by a generative language model. We show that our framework leads to improved control over the difficulty of the generated questions and better performance compared to baselines trained without rationales, both on automatic evaluation metrics and in human evaluation. Importantly, we show that this is achievable with a modest model size.