基本推理范式诱导语言模型的领域外泛化
Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models
AI总结：
本研究通过诱导基本推理范式提升语言模型的领域外泛化能力，实验表明方法在现实任务中性能提升显著。
摘要：
演绎、归纳和演绎是基本的推理范式，是人类逻辑思维的核心。尽管提高大型语言模型（LLM）的推理能力已经吸引了大量研究，但这些基本范式如何诱导泛化尚未系统地被探索。在本研究中，我们探讨了这些核心范式之间的相互作用如何影响LLM的推理行为。为此，我们首先收集了一个新的推理轨迹数据集，从符号任务中抽象出世界知识，每个任务针对三种基本范式之一。然后，我们研究了有效诱导这些技能进入LLM的方法。我们实验了多种方法，包括简单的微调，以及更复杂的增加模型深度或转换密集模型为专家混合的方法。我们全面评估了诱导模型在现实的领域外任务上的表现，这些任务完全用自然语言描述，并包含现实世界知识。我们的结果表明，我们的方法在现实任务中具有强大的泛化能力，性能提升显著（最高14.60）。
英文摘要：
Deduction, induction, and abduction are fundamental reasoning paradigms, core for human logical thinking. Although improving Large Language Model (LLM) reasoning has attracted significant research efforts, the extent to which the fundamental paradigms induce generalization has yet to be systematically explored. In this study, we shed light on how the interplay between these core paradigms influences LLMs' reasoning behavior. To this end, we first collect a new dataset of reasoning trajectories from symbolic tasks, each targeting one of the three fundamental paradigms, to abstract from concrete world knowledge. Then, we investigate effective ways for inducing these skills into LLMs. We experiment with a battery of methods including simple fine-tuning, and more complex approaches to increase model depth, or transform a dense model to a mixture-of-experts. We comprehensively evaluate induced models on realistic out-of-domain tasks, that are entirely formulated in natural language and contain real-world knowledge. Our results reveal that our approach yields strong generalizability with substantial performance gains (up to $14.60$) across realistic tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
