# Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers

arXiv: https://arxiv.org/abs/2210.11265 · HTML: https://mlsanity.com/paper/2210.11265/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Placed in

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

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [DEMix Layers: Disentangling Domains for Modular Language Modeling](https://mlsanity.com/paper/2108.05036/) (2021)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://mlsanity.com/paper/2004.04494/) (2020)
- [Language Model Cascades](https://mlsanity.com/paper/2207.10342/) (2022)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [AR-LSAT: Investigating Analytical Reasoning of Text](https://mlsanity.com/paper/2104.06598/) (2021)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)

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

- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming](https://mlsanity.com/paper/2507.15378/) (2025)
- [Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria](https://mlsanity.com/paper/2508.01763/) (2025)

## Abstract (arXiv)

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation module (automatic thinking) and reasoning modules (controlled thinking) are decoupled to capture different levels of cognition. Upon the top of the representation module, the pre-trained reasoning modules are modular and professional in specific and fundamental reasoning skills (e.g., logic, simple QA, etc). To mimic the controlled compositional thinking process, different reasoning modules are dynamically activated and composed in both parallel and cascaded manners to control what reasoning skills are activated and how deep the reasoning process will be reached to solve the current problems. The unified reasoning framework solves multiple tasks with a single model, and is trained and inferred in an end-to-end manner. Evaluated on 11 datasets requiring different reasoning skills and complexity, ReasonFormer demonstrates substantial performance boosts, revealing the compositional reasoning ability. Few-shot experiments exhibit better generalization ability by learning to compose pre-trained skills for new tasks with limited data, and decoupling the representation module and the reasoning modules. Further analysis shows the modularity of reasoning modules as different tasks activate distinct reasoning skills at different reasoning depths.