Roderick I. Swaab

Ray Friedman, Jaewoo Cho, Jeanne Brett et al.

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.

Daniel M. Romero, Roderick I. Swaab, Brian Uzzi et al.

The current research used the contexts of U.S. presidential debates and negotiations to examine whether matching the linguistic style of an opponent in a two-party exchange affects the reactions of third-party observers. Building off communication accommodation theory (CAT), interaction alignment theory (IAT), and processing fluency, we propose that language style matching (LSM) will improve subsequent third-party evaluations because matching an opponent's linguistic style reflects greater perspective taking and will make one's arguments easier to process. In contrast, research on status inferences predicts that LSM will negatively impact third-party evaluations because LSM implies followership. We conduct two studies to test these competing hypotheses. Study 1 analyzed transcripts of U.S. presidential debates between 1976 and 2012 and found that candidates who matched their opponent's linguistic style increased their standing in the polls. Study 2 demonstrated a causal relationship between LSM and third-party observer evaluations using negotiation transcripts.