将大型语言模型表征为知识密集型任务的合理化生成器
Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks
AI总结:
本研究探究LLM为知识密集型任务生成知识引导合理化解释的能力,发现其生成的解释优于众包版本但仍有不足,且错误预测的解释会降低人类信任,据此提出两阶段审查流水线以实现可信推理生成。
摘要:
大型语言模型(LLMs)擅长在极少任务特定监督下生成流畅文本。然而,它们为知识密集型任务提供有充分依据的合理化解释的能力仍未得到充分探索。这类任务(如常识多项选择题)需要基于世界知识的推理过程,以支持预测并反驳其他选项。我们研究了以少样本方式使用专家撰写的示例,生成自然语言形式的知识引导合理化解释的任务。令人惊讶的是,众包工作者更偏好知识支撑的合理化解释,而非众包生成的合理化解释,理由是前者具备事实准确性、充分性和全面的反驳性。尽管LLMs生成的合理化解释更受青睐,但在简洁性和新颖性方面仍需进一步改进。在另一项研究中,我们展示了对模型错误预测的合理化解释会如何削弱人类对LLM生成的合理化解释的信任。受这些观察结果的启发,我们构建了一个两阶段流水线,用于审查任务预测并在生成合理化解释前排除潜在的错误决策,从而实现可信的推理过程生成。
英文摘要:
Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks, like commonsense multiple-choice questions, require rationales based on world knowledge to support predictions and refute alternate options. We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner. Surprisingly, crowd-workers preferred knowledge-grounded rationales over crowdsourced rationalizations, citing their factuality, sufficiency, and comprehensive refutations. Although LLMs-generated rationales were preferable, further improvements in conciseness and novelty are required. In another study, we show how rationalization of incorrect model predictions erodes humans' trust in LLM-generated rationales. Motivated by these observations, we create a two-stage pipeline to review task predictions and eliminate potential incorrect decisions before rationalization, enabling trustworthy rationale generation.
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。