AI-Mediated Dispute Resolution
Proceedings of the AAAI Symposium Series · 28.05.2025 · 5 (1) · 67-70
DOI: 10.1609/aaaiss.v5i1.35558 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 28.05.2025. Verfasst von James Hale und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
We examine the effectiveness of large language model (LLM) mediations in the under-studied dispute resolution domain. We first used a new corpus of dispute resolutions, KODIS, to investigate if LLMs can correctly identify whether to intervene. We find evidence that GPT as a mediator picks up on salient aspects of a dispute, such as Frustration and whether the disputants ultimately come to a resolution or stall at an impasse --- intervening significantly more so in cases of high frustration and impasse. Afterward, we ran a user study to compare GPT mediations against those of novice human mediators. We find participants agreed GPT's mediations were more likely to lead to resolution; were better positioned in the dialog; had better justification than human-crafted ones; and, on a forced choice, were generally more effective than novice human mediations.
Zitieren
APA
Hale, J., Kim, H., Choi, A., & Gratch, J. (2025). AI-Mediated Dispute Resolution. Proceedings of the AAAI Symposium Series, 5(1), 67-70. https://doi.org/10.1609/aaaiss.v5i1.35558
Vancouver
Hale J, Kim H, Choi A, Gratch J. AI-Mediated Dispute Resolution. Proceedings of the AAAI Symposium Series. 2025;5(1):67-70. doi:10.1609/aaaiss.v5i1.35558
BibTeX
@article{Hale2025,
author = {Hale, James and Kim, HanMoe and Choi, Ahyoung and Gratch, Jonathan},
title = {AI-Mediated Dispute Resolution},
journal = {Proceedings of the AAAI Symposium Series},
year = {2025},
volume = {5},
number = {1},
pages = {67--70},
doi = {10.1609/aaaiss.v5i1.35558}
}
EUVIMED