多智能体喜剧俱乐部:探究社区讨论对LLM幽默生成的影响
Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation
AI总结:
本研究通过多智能体实验探讨社区讨论对LLM生成幽默的影响,发现讨论条件在Craft/Clarity和社会反应指标上显著优于基线条件。
摘要:
先前的工作已探讨了多轮交互和反馈对LLM写作的影响,但评估仍主要集中在提示和局部反馈上,导致在线社区中的持续公众反应未被充分考察。我们测试了广播社区讨论是否能改善单口喜剧写作,在受控的多智能体沙盒中:在讨论条件下,评论员和观众的讨论被记录、过滤、存储为社会记忆,并在后续生成中被检索以进行条件设置,而基线条件则省略讨论。在50轮(250对单口喜剧)中,由五位专家标注员通过A/B偏好和15项评分标准进行评估,讨论在75.6%的实例中获胜,并提高了Craft/Clarity(Δ=0.440)和社会反应(Δ=0.422),偶尔还增加了攻击性幽默。
英文摘要:
Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor.
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。