arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.19764cs.CL
收藏

信念修正:大型语言模型推理的适应性

Belief Revision: The Adaptability of Large Language Models Reasoning

Hong Kong University of Science and Technology(香港科技大学);Clear Water Bay(清水湾)

Bryan Wilie, Samuel Cahyawijaya, Etsuko Ishii, Junxian He, Pascale Fung

AI总结:

本文提出Belief-R数据集和delta推理框架,通过评估约30个语言模型发现其在信念修正上普遍存在困难,并揭示了更新能力与避免不必要更新之间的关键权衡,强调提升模型适应变化信息的重要性。

摘要:

从文本中进行推理的能力对于现实世界的自然语言处理应用至关重要。现实场景往往涉及不完整或不断变化的数据。作为回应,个体会相应地更新自己的信念和理解。然而,现有的大多数评估都假设语言模型(LMs)在信息一致的条件下运行。我们引入了Belief-R,这是一个新数据集,旨在测试语言模型在获得新证据时的信念修正能力。受人类抑制先前推断方式的启发,该任务在新提出的delta推理(ΔR)框架内评估语言模型。Belief-R包含一系列前提序列,旨在模拟额外信息可能使语言模型先前得出的结论需要被修正的场景。我们评估了约30个语言模型在多种提示策略下的表现,发现语言模型通常难以根据新信息适当地修正其信念。此外,善于更新的模型在不需要更新的场景中往往表现不佳,这凸显了一个关键的权衡。这些见解强调了提高语言模型对变化信息的适应性的重要性,这是迈向更可靠人工智能系统的一步。

英文摘要:

The capability to reason from text is crucial for real-world NLP applications. Real-world scenarios often involve incomplete or evolving data. In response, individuals update their beliefs and understandings accordingly. However, most existing evaluations assume that language models (LMs) operate with consistent information. We introduce Belief-R, a new dataset designed to test LMs' belief revision ability when presented with new evidence. Inspired by how humans suppress prior inferences, this task assesses LMs within the newly proposed delta reasoning ($ΔR$) framework. Belief-R features sequences of premises designed to simulate scenarios where additional information could necessitate prior conclusions drawn by LMs. We evaluate $\sim$30 LMs across diverse prompting strategies and found that LMs generally struggle to appropriately revise their beliefs in response to new information. Further, models adept at updating often underperformed in scenarios without necessary updates, highlighting a critical trade-off. These insights underscore the importance of improving LMs' adaptiveness to changing information, a step toward more reliable AI systems.

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。

↑