TORSO让大模型无需示例就能自主推理，跨任务表现更稳定。
TORSO: Template-Oriented Reasoning Towards General Tasks
- 用模板引导模型激活内部推理能力，不依赖人工示例。
- 在多个基准测试中表现优异，生成的推理过程合理可信。
- 适合希望减少人工设计、提升模型泛化能力的研究者。
引导大语言模型在生成回答时模拟人类推理过程的方法，已成为使其以逐步方式解决复杂问题的有效手段，从而取得优越性能。然而，现有基于少量示例提示的方法严重依赖提供的样例，限制了模型自身推理能力的发挥。此外，构建特定任务的少量示例提示通常成本较高，且可能导致不同任务间不一致。本文提出模板导向推理（TORSO），通过模板激发模型利用其内在推理能力，在无需人工设计示例的情况下，对多种任务生成恰当响应。实验结果表明，TORSO在多个LLM基准上均表现出色，且推理过程合理。
原文摘要 · Abstract (English)
The approaches that guide Large Language Models (LLMs) to emulate human reasoning during response generation have emerged as an effective method for enabling them to solve complex problems in a step-by-step manner, thereby achieving superior performance. However, most existing approaches using few-shot prompts to generate responses heavily depend on the provided examples, limiting the utilization of the model's inherent reasoning capabilities. Moreover, constructing task-specific few-shot prompts is often costly and may lead to inconsistencies across different tasks. In this work, we introduce Template-Oriented Reasoning (TORSO), which elicits the model to utilize internal reasoning abilities to generate proper responses across various tasks without the need for manually crafted few-shot examples. Our experimental results demonstrate that TORSO achieves strong performance on diverse LLMs benchmarks with reasonable rationales.
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。