# Abstraction-of-Thought Makes Language Models Better Reasoners

arXiv: https://arxiv.org/abs/2406.12442 · HTML: https://mlsanity.com/paper/2406.12442/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 54 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [Best Practices and Lessons Learned on Synthetic Data](https://mlsanity.com/paper/2404.07503/) (2024)
- [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024)
- [Demystifying Chains, Trees, and Graphs of Thoughts](https://mlsanity.com/paper/2401.14295/) (2024)
- [Efficient Tool Use with Chain-of-Abstraction Reasoning](https://mlsanity.com/paper/2401.17464/) (2024)
- [PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning](https://mlsanity.com/paper/2305.13888/) (2023)
- [Conceptual and Unbiased Reasoning in Language Models](https://mlsanity.com/paper/2404.00205/) (2024)
- [Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning](https://mlsanity.com/paper/2307.02053/) (2023)
- [Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization](https://mlsanity.com/paper/2206.01532/) (2022)
- [AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph](https://mlsanity.com/paper/2311.09174/) (2023)
- [Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models](https://mlsanity.com/paper/2306.17820/) (2023)

## Built on by (most cited first, 11 of 11)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty](https://mlsanity.com/paper/2412.20251/) (2024)
- [Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective](https://mlsanity.com/paper/2412.12276/) (2024)
- [CC-LEARN: Cohort-based Consistency Learning](https://mlsanity.com/paper/2506.15662/) (2025)
- [Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models](https://mlsanity.com/paper/2501.02026/) (2025)
- [AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking](https://mlsanity.com/paper/2506.07751/) (2025)
- [Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience](https://mlsanity.com/paper/2505.05515/) (2025)
- [A Survey of Query Optimization in Large Language Models](https://mlsanity.com/paper/2412.17558/) (2024)
- [TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval](https://mlsanity.com/paper/2607.28498/) (2026)
- [From Language to Logic: A Bi-Level Framework for Structured Reasoning](https://mlsanity.com/paper/2507.08501/) (2025)
- [Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models](https://mlsanity.com/paper/2609.26610/) (2026)

## Abstract (arXiv)

Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning. However, eliciting language models to perform reasoning with abstraction remains unexplored. This paper seeks to bridge this gap by introducing a novel structured reasoning format called Abstraction-of-Thought (AoT). The uniqueness of AoT lies in its explicit requirement for varying levels of abstraction within the reasoning process. This approach could elicit language models to first contemplate on the abstract level before incorporating concrete details, which is overlooked by the prevailing step-by-step Chain-of-Thought (CoT) method. To align models with the AoT format, we present AoT Collection, a generic finetuning dataset consisting of 348k high-quality samples with AoT reasoning processes, collected via an automated and scalable pipeline. We finetune a wide range of language models with AoT Collection and conduct extensive evaluations on 23 unseen tasks from the challenging benchmark Big-Bench Hard. Experimental results indicate that models aligned to AoT reasoning format substantially outperform those aligned to CoT in many reasoning tasks.