An Application of Large Language Models to Coding Negotiation Transcripts
Computation and Language
2024-08-01 v1 Artificial Intelligence
Abstract
In recent years, Large Language Models (LLM) have demonstrated impressive capabilities in the field of natural language processing (NLP). This paper explores the application of LLMs in negotiation transcript analysis by the Vanderbilt AI Negotiation Lab. Starting in September 2022, we applied multiple strategies using LLMs from zero shot learning to fine tuning models to in-context learning). The final strategy we developed is explained, along with how to access and use the model. This study provides a sense of both the opportunities and roadblocks for the implementation of LLMs in real life applications and offers a model for how LLMs can be applied to coding in other fields.
Cite
@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}
}