Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 1, 2025Open Access

Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

MRMyrthe ReuverISIndira SenMMMatteo Melis

Discussion

Loading...

Member takes

Overview

This research investigates interactions between sexism experts and large language models, indicating valuable engagement strategies.

Key Points

  • LLM interactions resulted in more detailed definitions of sexism, enhancing understanding and application.
  • Expert-written definitions often underperformed compared to those generated by the LLMs during detection tasks.
  • Experiments included two interactive assessments with nine experts and a large dataset for classification analysis.
  • Co-created definitions showed improvement in classification performance, particularly for novice LLM users.

Cite This Study

Reuver et al. (2025) studied this question.

synapsesocial.com/papers/68dd91c7fe798ba2fc498484https://doi.org/10.48550/arxiv.2504.15392
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Bilingual Sexism Classification: Fine-Tuned XLM-RoBERTa and GPT-3.5 Few-Shot Learning2024
  2. 2Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes2024
  3. 3A Transparent Pipeline for Identifying Sexism in Social Media: Combining Explainability with Model Prediction2024 · 3 citations
  4. 4Evaluation of Large Language Models: STEM education and Gender Stereotypes2024 · 3 citations
  5. 5Evaluating LLMs for Gender Disparities in Notable Persons2024 · 2 citations