AI可能存在认知偏差：基于大语言模型的批量相关性评估中阈值启动效应的探索性研究
AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment
AI总结：
该研究通过TREC 2019数据集实验发现，大语言模型在批量相关性判断中存在类似人类的阈值启动认知偏差，提示相关设计评估需考虑此类偏差。
摘要：
认知偏差是思维中导致非理性判断和问题决策的系统性偏差，已在多个领域得到广泛研究。近年来，大语言模型（LLM）展现出先进的理解能力，但可能从训练数据中继承人类偏差。目前LLM的社会偏差已被充分研究，但认知偏差受到的关注较少，现有研究多聚焦于特定场景，认知偏差在各类决策情境下对LLM的更广泛影响仍有待充分探究。我们研究了LLM在相关性判断中是否受阈值启动效应影响，相关性判断是信息检索（IR）领域的核心任务与广受讨论的研究主题。启动效应指接触特定刺激会无意识地影响后续行为与决策。我们的实验采用TREC 2019 Deep Learning段落赛道数据集的10个主题，在不同文档相关性分数、批量长度和LLM模型（包括GPT-3.5、GPT-4、LLaMa2-13B和LLaMa2-70B）下测试AI判断。结果显示，无论采用何种组合与模型，若前期文档相关性高，LLM倾向于给后期文档更低分数，反之亦然。我们的发现表明，LLM的判断与人类判断类似，也受阈值启动偏差影响，并建议研究人员与系统工程师在设计、评估和审计IR任务及其他领域的LLM时，应考虑潜在的类人认知偏差。
英文摘要：
Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding capabilities but may inherit human biases from their training data. While social biases in LLMs have been well-studied, cognitive biases have received less attention, with existing research focusing on specific scenarios. The broader impact of cognitive biases on LLMs in various decision-making contexts remains underexplored. We investigated whether LLMs are influenced by the threshold priming effect in relevance judgments, a core task and widely-discussed research topic in the Information Retrieval (IR) coummunity. The priming effect occurs when exposure to certain stimuli unconsciously affects subsequent behavior and decisions. Our experiment employed 10 topics from the TREC 2019 Deep Learning passage track collection, and tested AI judgments under different document relevance scores, batch lengths, and LLM models, including GPT-3.5, GPT-4, LLaMa2-13B and LLaMa2-70B. Results showed that LLMs tend to give lower scores to later documents if earlier ones have high relevance, and vice versa, regardless of the combination and model used. Our finding demonstrates that LLM%u2019s judgments, similar to human judgments, are also influenced by threshold priming biases, and suggests that researchers and system engineers should take into account potential human-like cognitive biases in designing, evaluating, and auditing LLMs in IR tasks and beyond.
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。
