提出思维语言提示法，缓解大模型推理中的语言偏差问题。
On the Thinking-Language Modeling Gap in Large Language Models
- 用思维语言（LoT）重构提示，让模型重新组织信息表达顺序。
- 在多类推理任务中，显著降低语言建模偏差，提升准确率。
- 适合关注大模型可解释性与逻辑推理的研究者使用。
系统2推理是智能的核心特征，依赖于缓慢且逻辑化的思维过程。人类通过思维语言将推理组织为因果链条。尽管大语言模型（LLMs）能从大规模自然语言预训练中激发系统2推理，但本文揭示其存在思维与语言建模之间的显著差距：语言作为知识共享工具，会引入偏见，导致模型仅关注前提的有偏部分。为此，我们提出语言-思维（Language-of-Thoughts, LoT）提示策略，要求模型调整所有相关信息的表达顺序与词元使用，而非直接生成思维链。实验表明，该方法有效缓解了语言建模偏见，在多种推理任务上均显著提升性能。
原文摘要 · Abstract (English)
System 2 reasoning is one of the defining characteristics of intelligence, which requires slow and logical thinking. Human conducts System 2 reasoning via the language of thoughts that organizes the reasoning process as a causal sequence of mental language, or thoughts. Recently, it has been observed that System 2 reasoning can be elicited from Large Language Models (LLMs) pre-trained on large-scale natural languages. However, in this work, we show that there is a significant gap between the modeling of languages and thoughts. As language is primarily a tool for humans to share knowledge and thinking, modeling human language can easily absorb language biases into LLMs deviated from the chain of thoughts in minds. Furthermore, we show that the biases will mislead the eliciting of "thoughts" in LLMs to focus only on a biased part of the premise. To this end, we propose a new prompt technique termed Language-of-Thoughts (LoT) to demonstrate and alleviate this gap. Instead of directly eliciting the chain of thoughts from partial information, LoT instructs LLMs to adjust the order and token used for the expressions of all the relevant information. We show that the simple strategy significantly reduces the language modeling biases in LLMs and improves the performance of LLMs across a variety of reasoning tasks.
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。