# Self-supervised Analogical Learning using Language Models

arXiv: https://arxiv.org/abs/2502.00996 · HTML: https://mlsanity.com/paper/2502.00996/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2025.

## Built on by (most cited first, 2 of 2)

- [Semi-structured LLM Reasoners Can Be Rigorously Audited](https://mlsanity.com/paper/2505.24217/) (2025)
- [CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning](https://mlsanity.com/paper/2512.18857/) (2025)

## Abstract (arXiv)

Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that they can successfully solve. Such observations motivate us to propose methods that encourage models to understand the high-level and abstract reasoning processes during training instead of only the final answer. This way, models can transfer the exact solution to similar cases, regardless of their relevance to the pre-training data distribution. In this work, we propose SAL, a self-supervised analogical learning framework. SAL mimics the human analogy process and trains models to explicitly transfer high-quality symbolic solutions from cases that they know how to solve to other rare cases in which they tend to fail more. We show that the resulting models after SAL learning outperform base language models on a wide range of reasoning benchmarks, such as StrategyQA, GSM8K, and HotpotQA, by 2% to 20%. At the same time, we show that our model is more generalizable and controllable through analytical studies.