大型语言模型应用于编码谈判记录
计算与语言
2024-08-01 v1 人工智能
摘要
近年来，大型语言模型（LLM）在自然语言处理（NLP）领域展现了令人印象深刻的能力。本文探讨了LLM在 Vanderbilt AI 谈判实验室的谈判记录分析中的应用。自2022年9月起，我们使用多种策略对LLM进行了从零样本学习到微调模型的 in-context learning 应用。我们解释了所开发的最终策略，并说明如何访问和使用该模型。本研究提供了关于LLM在实际应用中机遇和障碍的 sense，并为LLM在其他领域的编码应用提供了模型。
关键词
引用
@article{arxiv.2407.21037,
title = {An Application of Large Language Models to Coding Negotiation Transcripts},
author = {Ray Friedman and Jaewoo Cho and Jeanne Brett and Xuhui Zhan and Ningyu Han and Sriram Kannan and Yingxiang Ma and Jesse Spencer-Smith and Elisabeth Jäckel and Alfred Zerres and Madison Hooper and Katie Babbit and Manish Acharya and Wendi Adair and Soroush Aslani and Tayfun Aykaç and Chris Bauman and Rebecca Bennett and Garrett Brady and Peggy Briggs and Cheryl Dowie and Chase Eck and Igmar Geiger and Frank Jacob and Molly Kern and Sujin Lee and Leigh Anne Liu and Wu Liu and Jeffrey Loewenstein and Anne Lytle and Li Ma and Michel Mann and Alexandra Mislin and Tyree Mitchell and Hannah Martensen née Nagler and Amit Nandkeolyar and Mara Olekalns and Elena Paliakova and Jennifer Parlamis and Jason Pierce and Nancy Pierce and Robin Pinkley and Nathalie Prime and Jimena Ramirez-Marin and Kevin Rockmann and William Ross and Zhaleh Semnani-Azad and Juliana Schroeder and Philip Smith and Elena Stimmer and Roderick Swaab and Leigh Thompson and Cathy Tinsley and Ece Tuncel and Laurie Weingart and Robert Wilken and JingJing Yao and Zhi-Xue Zhang},
journal= {arXiv preprint arXiv:2407.21037},
year = {2024}
}