识别局限性:探究大型语言模型中的不可行性
Recognizing Limits: Investigating Infeasibility in Large Language Models
AI总结:
针对大型语言模型(LLMs)因无法处理超出能力的查询而生成错误或编造响应的问题,本文提出四大不可行任务类别,构建并基准测试新数据集,探索微调提升拒绝能力的潜力,为改进LLMs实际应用性能提供方向。
摘要:
大型语言模型(LLMs)在各类任务中表现出色,但常无法处理超出其知识与能力的查询,导致错误或编造的响应。本文旨在解决LLMs需识别并拒绝因请求超出其能力而不可行的任务这一需求。我们将LLMs的不可行任务概念化为四大类,涵盖了先前文献中识别的与幻觉相关的各类挑战。我们开发并基准测试了一个包含多样不可行与可行任务的新数据集,以评估多个LLMs拒绝不可行任务的能力。此外,我们还探索了通过微调提升LLMs拒绝能力的潜力。实验验证了训练模型的有效性,为改进LLMs在实际应用中的性能提供了有前景的方向。
英文摘要:
Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the requests surpassing their capabilities. We conceptualize four main categories of infeasible tasks for LLMs, which cover a broad spectrum of hallucination-related challenges identified in prior literature. We develop and benchmark a new dataset comprising diverse infeasible and feasible tasks to evaluate multiple LLMs' abilities to decline infeasible tasks. Furthermore, we explore the potential of increasing LLMs' refusal capabilities with fine-tuning. Our experiments validate the effectiveness of the trained models, suggesting promising directions for improving the performance of LLMs in real-world applications.
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。