Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915925320531968 |
|---|---|
| author | Majumdar, Ayan Chen, Feihao Li, Jinghui Wang, Xiaozhen |
| author_facet | Majumdar, Ayan Chen, Feihao Li, Jinghui Wang, Xiaozhen |
| contents | Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although prior work has investigated biases in text datasets and related detection methods, these studies remain narrow in scope. They typically focus on a single content type (e.g., hate speech), cover limited demographic axes, overlook biases affecting multiple demographics simultaneously, and analyze limited techniques. Consequently, practitioners lack a holistic understanding of the strengths and limitations of recent large language models (LLMs) for automated bias detection. In this study, we conduct a comprehensive benchmark study on English texts to assess the ability of LLMs in detecting demographic-targeted social biases. To align with regulatory requirements, we frame bias detection as a multi-label task of detecting targeted identities using a demographic-focused taxonomy. We then systematically evaluate models across scales and techniques, including prompting, in-context learning, and fine-tuning. Using twelve datasets spanning diverse content types and demographics, our study demonstrates the promise of fine-tuned smaller models for scalable detection. However, our analyses also expose persistent gaps across demographic axes and multi-demographic targeted biases, underscoring the need for more effective and scalable detection frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04641 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study Majumdar, Ayan Chen, Feihao Li, Jinghui Wang, Xiaozhen Computation and Language Computers and Society Machine Learning Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although prior work has investigated biases in text datasets and related detection methods, these studies remain narrow in scope. They typically focus on a single content type (e.g., hate speech), cover limited demographic axes, overlook biases affecting multiple demographics simultaneously, and analyze limited techniques. Consequently, practitioners lack a holistic understanding of the strengths and limitations of recent large language models (LLMs) for automated bias detection. In this study, we conduct a comprehensive benchmark study on English texts to assess the ability of LLMs in detecting demographic-targeted social biases. To align with regulatory requirements, we frame bias detection as a multi-label task of detecting targeted identities using a demographic-focused taxonomy. We then systematically evaluate models across scales and techniques, including prompting, in-context learning, and fine-tuning. Using twelve datasets spanning diverse content types and demographics, our study demonstrates the promise of fine-tuned smaller models for scalable detection. However, our analyses also expose persistent gaps across demographic axes and multi-demographic targeted biases, underscoring the need for more effective and scalable detection frameworks. |
| title | Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study |
| topic | Computation and Language Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2510.04641 |