arXiv：cs.LG· Mohammed Azeez Khan, Aaron Dsouza, Ashutosh Mishra, Ummul Faiz Z. Bibi, Neha K. Nair, Amar Kumar Behera·· 11 小时前
Llama 3.1 8B Instruct 与人类引导者在协作设计会议中的行为对比
Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison
AI 导读
研究对比了 AMI Meeting Corpus 中人类项目经理的引导发言与 Llama 3.1 8B Instruct 在 199 组配对情境下的表现，人类在上下文语义距离（r = 0.644）和共情与模糊限制词密度（r = 0.203）上更高，后者主要由模糊限制词驱动。
正文
Abstract:Large language models (LLMs) are increasingly being explored as facilitators of group discussion and collaborative work, but the behavioral differences between LLM-generated and human facilitation remain insufficiently characterized. We compare human Project Manager facilitation turns from scenario-based collaborative design meetings with Llama 3.1 8B Instruct responses across 199 paired contexts from the AMI Meeting Corpus. The analysis covers five confirmatory dimensions: contextual semantic distance, a lexical elaboration proxy, empathyand-hedge lexical density, topic divergence, and phase-vocabulary alignment. An exploratory directiveness measure failed domain validation and is not interpreted. The sampled human Project Manager turns were higher on contextual semantic distance (r = 0.644) and on empathyand-hedge lexical density (r = 0.203). The second contrast is carried mainly by hedge terms, so we read it as lexical hedging rather than psychological empathy. Llama-generated facilitation was higher on topic divergence (r = 0.703), the lexical elaboration proxy (r = 0.288; lengthconfounded), and instruction-conditioned phase-vocabulary alignment (r = 0.382). A secondary no-phase check left the Llama-higher phase contrast in place. The system prompt still requested a facilitation move, so that check is not evidence of spontaneous phase awareness. These differences should not be interpreted as a ranking of facilitation quality. The resulting behavioral profile provides a reference point for later comparisons of LLM facilitators, human facilitators, prompts, models, and collaborative settings.
| Comments: | 17 pages, 7 figures, 6 tables |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.13082 [cs.LG] |
| (or arXiv:2610.13082v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13082 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aaron D'Souza [view email]
[v1]
Fri, 9 Oct 2026 06:36:45 UTC (1,207 KB)
来源：arXiv：cs.LG · arxiv.org