Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health

TL;DR

This paper examines how Western-centric benchmarks for evaluating large language models in sexual and reproductive health overlook cultural differences, highlighting the need for culturally adaptive evaluation methods.

Contribution

It reveals the limitations of current benchmarks in diverse cultural contexts and advocates for culturally sensitive evaluation frameworks for health-related LLMs.

Findings

Current benchmarks rated responses low despite cultural appropriateness

Western bias affects legal, dietary, and cost-related responses

Culturally adaptive evaluation frameworks are needed

Abstract

Large Language Models (LLMs) have been positioned as having the potential to expand access to health information in the Global South, yet their evaluation remains heavily dependent on benchmarks designed around Western norms. We present insights from a preliminary benchmarking exercise with a chatbot for sexual and reproductive health (SRH) for an underserved community in India. We evaluated using HealthBench, a benchmark for conversational health models by OpenAI. We extracted 637 SRH queries from the dataset and evaluated on the 330 single-turn conversations. Responses were evaluated using HealthBench's rubric-based automated grader, which rated responses consistently low. However, qualitative analysis by trained annotators and public health experts revealed that many responses were actually culturally appropriate and medically accurate. We highlight recurring issues, particularly a Western bias, such as for legal framing and norms (e.g., breastfeeding in public), diet assumptions (e.g., fish safe to eat during pregnancy), and costs (e.g., insurance models). Our findings demonstrate the limitations of current benchmarks in capturing the effectiveness of systems built for different cultural and healthcare contexts. We argue for the development of culturally adaptive evaluation frameworks that meet quality standards while recognizing needs of diverse populations.