arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.10573cs.AI
收藏

无效逻辑,等效增益:语言模型提示中推理的反常性

Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting

Stanford University(斯坦福大学)

Rylan Schaeffer, Kateryna Pistunova, Samar Khanna, Sarthak Consul, Sanmi Koyejo

AI总结:

针对思维链提示提升性能的机制争议,研究在BIG-Bench Hard任务集上验证发现逻辑无效的CoT提示与有效提示增益相近,指出性能提升源于有效推理之外的因素。

摘要:

语言模型可通过提示(prompting)进行问题推理,从而显著提升性能。然而,这类提示为何能提升性能尚不明确。近期研究显示,使用逻辑上无效的思维链(Chain-of-Thought, CoT)提示提升性能的效果几乎与逻辑有效的CoT提示相当,且将CoT提示中的问题特定信息替换为抽象信息或分布外信息通常不会损害性能。批评者回应称,这些发现基于的任务数量太少且过于简单,无法得出有意义的结论。为解决这一争议,我们在BIG-Bench基准中最难的任务集BIG-Bench Hard(BBH)上,测试了逻辑无效的CoT提示是否能带来与逻辑有效提示同等水平的性能增益。我们发现,逻辑无效的推理提示在BBH任务上确实能实现与逻辑有效推理提示相似的性能增益。我们还发现,先前研究使用的部分CoT提示存在逻辑错误。这表明,性能提升的驱动因素是逻辑有效推理之外的协变量。

英文摘要:

Language models can be prompted to reason through problems in a manner that significantly improves performance. However, \textit{why} such prompting improves performance is unclear. Recent work showed that using logically \textit{invalid} Chain-of-Thought (CoT) prompting improves performance almost as much as logically \textit{valid} CoT prompting, and that editing CoT prompts to replace problem-specific information with abstract information or out-of-distribution information typically doesn't harm performance. Critics have responded that these findings are based on too few and too easily solved tasks to draw meaningful conclusions. To resolve this dispute, we test whether logically invalid CoT prompts offer the same level of performance gains as logically valid prompts on the hardest tasks in the BIG-Bench benchmark, termed BIG-Bench Hard (BBH). We find that the logically \textit{invalid} reasoning prompts do indeed achieve similar performance gains on BBH tasks as logically valid reasoning prompts. We also discover that some CoT prompts used by previous works contain logical errors. This suggests that covariates beyond logically valid reasoning are responsible for performance improvements.

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。

↑