每个( bot )都会犯错：将大五人格、情境和语气编码到LLM聊天机器人恢复代码框架中
Every(bot) Makes Mistakes: Coding Big Five Personalities, Context, and Tone into an LLM Chatbot Recovery Code Framework
AI总结：
本文提出一个结合大五人格、情境和语气的LLM聊天机器人恢复代码框架，通过实验验证其在提升错误恢复质量方面的有效性。
摘要：
尽管在分类器、参数和安全保障方面进行了精心设计，人机交互中的错误仍不可避免。糟糕的错误恢复会破坏交互流程，损害用户信任并降低用户参与度。尽管现有研究已探讨了LLM恢复、语气、情境和人格作为独立设计维度，但没有研究将这些变量整合到结构化指导框架中。本文提出一种恢复代码，将四种常见的LLM聊天机器人任务情境映射到相关的人格特质（四个大五人格：尽责性、宜人性、开放性和外向性）、语气和三阶段恢复指令。还设计了一个恢复评估标准，包含三个维度（恢复质量、语气一致性、适当性）和九个子维度。方法是探索性的，未使用参与者。采用两组条件的组内设计：条件A（基线，未编码），四个独立的Claude Sonnet 4.6代理未接受恢复代码训练；条件B（编码），四个独立的Claude Sonnet 4.6模型在恢复代码上进行了训练。在两个条件下使用了相同的'用户'提示和错误场景。八个LLM评估者代理使用评估标准评估恢复响应，为每个子维度评分。结果发现，编码后的恢复响应在恢复质量方面平均提高了27.8%（76.7%）相比基线响应（48.9%）。条件B在适当性维度表现最强（83.3%），在人格适当性（75% vs 50%）和提供解释（60% vs 20%）方面有显著改进。这些发现表明，结构化的人格、情境和语气指导的恢复代码可以被LLM聊天机器人成功学习和应用，以提高在不同情境任务中的错误恢复质量。
英文摘要：
Despite careful design involving classifiers, parameters, and safeguarding, errors during human/AI interaction are not rare. Poor error recovery can disrupt interaction flow, damage user trust, and decrease user engagement. Whilst existing work has explored LLM recovery, tone, context, and personality as separate design dimensions, no existing work has combined these variables into a structured guidance framework. This paper presents a recovery code that maps four common LLM chatbot task contexts to associated personality traits (four Big Five personalities: Conscientiousness, Agreeableness, Openness, and Extraversion), tones, and three-stage recovery instructions. A recovery evaluation rubric was also designed, comprising three dimensions (Recovery quality, Tone alignment, and Appropriateness) and nine sub-dimensions. The methodology is exploratory, with no participants used. A between-subjects design was employed across two conditions: Condition A (baseline, uncoded), four separate Claude Sonnet 4.6 agents received no recovery code training; Condition B (coded), four separate Claude Sonnet 4.6 models were trained on the recovery code. Identical 'user' prompts and error scenarios were used across both conditions. Eight LLM evaluator agents assessed the recovery responses using the evaluation rubric, producing scores out of 5 for each sub-dimension. Results found a 27.8% average performance increase in coded recovery responses (76.7%) compared to baseline responses (48.9%). Condition B performed strongest in the appropriateness dimension (83.3%), with notable improvement in personality appropriateness (75% versus 50%) and providing explanation (60% versus 20%). These findings suggest that structured personality, context, and tone-informed recovery codes can be successfully learnt and applied by LLM chatbots to improve error recovery quality across varying contextual tasks.
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。
