大模型在关系抽取中倾向保守，常选'无关系'导致信息丢失。
Conservative Bias in Large Language Models: Measuring Relation Predictions
- 通过对比不同提示类型，发现模型更倾向选安全标签
- 保守偏差发生频率是幻觉的两倍
- 适合关注模型可靠性与信息损失的研究者
大型语言模型在关系抽取任务中表现出显著的保守偏差，当存在合适选项时仍频繁选择'无关系'标签。这种行为虽能避免错误关联，但若推理未显式输出，则会造成重大信息损失。我们系统评估了多种提示、数据集和关系类型下的这一权衡，引入'霍布森选择'概念描述模型在安全与信息量之间权衡的场景。研究发现，保守偏差的发生频率是幻觉的两倍。为量化该效应，我们使用SBERT和LLM提示比较受限提示下保守行为与半受限及开放式提示生成标签之间的语义相似性。
原文摘要 · Abstract (English)
Large language models (LLMs) exhibit pronounced conservative bias in relation extraction tasks, frequently defaulting to No_Relation label when an appropriate option is unavailable. While this behavior helps prevent incorrect relation assignments, our analysis reveals that it also leads to significant information loss when reasoning is not explicitly included in the output. We systematically evaluate this trade-off across multiple prompts, datasets, and relation types, introducing the concept of Hobson's choice to capture scenarios where models opt for safe but uninformative labels over hallucinated ones. Our findings suggest that conservative bias occurs twice as often as hallucination. To quantify this effect, we use SBERT and LLM prompts to capture the semantic similarity between conservative bias behaviors in constrained prompts and labels generated from semi-constrained and open-ended prompts.
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。