让大模型学会举一反三，提升罕见问题的推理能力
Self-supervised Analogical Learning using Language Models
- 通过类比学习，引导模型迁移已掌握的解题思路
- 在多个推理任务上提升2%至20%的准确率
- 增强模型泛化性与可控性，适合复杂推理场景
大型语言模型存在推理不一致的问题：在训练数据中不常见的场景下表现较差，即使相似的推理路径在常见情况下已被成功解决。为此，我们提出自监督类比学习框架SAL，模仿人类类比思维，训练模型将已掌握的高质量符号化解题方案迁移到罕见但结构相似的问题中。实验表明，经过SAL训练的模型在StrategyQA、GSM8K和HotpotQA等推理基准上，相比基线模型提升2%至20%。同时，分析显示该模型具备更强的泛化性和可控性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。