Automate or Assist? The Role of Computational Models in Identifying Gendered Discourse in US Capital Trial Transcripts

TL;DR

This study explores how computational models can assist legal experts in identifying gender-biased language in US capital trial transcripts, emphasizing the models' role in reflection and consensus-building rather than replacement.

Contribution

The paper demonstrates that computational models are most valuable for assisting legal experts in complex bias annotation tasks, rather than fully automating the process.

Findings

Models help experts reflect on their own biases.

Models facilitate consensus on annotation rules.

Automation is not a complete replacement for expert judgment.

Abstract

The language used by US courtroom actors in criminal trials has long been studied for biases. However, systematic studies for bias in high-stakes court trials have been difficult, due to the nuanced nature of bias and the legal expertise required. Large language models offer the possibility to automate annotation. But validating the computational approach requires both an understanding of how automated methods fit in existing annotation workflows and what they really offer. We present a case study of adding a computational model to a complex and high-stakes problem: identifying gender-biased language in US capital trials for women defendants. Our team of experienced death-penalty lawyers and NLP technologists pursue a three-phase study: first annotating manually, then training and evaluating computational models, and finally comparing expert annotations to model predictions. Unlike many typical NLP tasks, annotating for gender bias in months-long capital trials is complicated, with many individual judgment calls. Contrary to standard arguments for automation that are based on efficiency and scalability, legal experts find the computational models most useful in providing opportunities to reflect on their own bias in annotation and to build consensus on annotation rules. This experience suggests that seeking to replace experts with computational models for complex annotation is both unrealistic and undesirable. Rather, computational models offer valuable opportunities to assist the legal experts in annotation-based studies.