Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.20102 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908793201229824 |
|---|---|
| author | Rezaei, Amirhossein Haji Mohammad Shakeri, Zahra |
| author_facet | Rezaei, Amirhossein Haji Mohammad Shakeri, Zahra |
| contents | Engineering sustainable and equitable healthcare requires medical language models that do not change clinically correct diagnoses when presented with non-decisive cultural information. We introduce a counterfactual benchmark that expands 150 MedQA test items into 1650 variants by inserting culture-related (i) identifier tokens, (ii) contextual cues, or (iii) their combination for three groups (Indigenous Canadian, Middle-Eastern Muslim, Southeast Asian), plus a length-matched neutral control, where a clinician verified that the gold answer remains invariant in all variants. We evaluate GPT-5.2, Llama-3.1-8B, DeepSeek-R1, and MedGemma (4B/27B) under option-only and brief-explanation prompting. Across models, cultural cues significantly affect accuracy (Cochran's Q, $p<10^-14$), with the largest degradation when identifier and context co-occur (up to 3-7 percentage points under option-only prompting), while neutral edits produce smaller, non-systematic changes. A human-validated rubric ($κ=0.76$) applied via an LLM-as-judge shows that more than half of culturally grounded explanations end in an incorrect answer, linking culture-referential reasoning to diagnostic failure. We release prompts and augmentations to support evaluation and mitigation of culturally induced diagnostic errors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20102 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Counterfactual Cultural Cues Reduce Medical QA Accuracy in LLMs: Identifier vs Context Effects Rezaei, Amirhossein Haji Mohammad Shakeri, Zahra Computation and Language Engineering sustainable and equitable healthcare requires medical language models that do not change clinically correct diagnoses when presented with non-decisive cultural information. We introduce a counterfactual benchmark that expands 150 MedQA test items into 1650 variants by inserting culture-related (i) identifier tokens, (ii) contextual cues, or (iii) their combination for three groups (Indigenous Canadian, Middle-Eastern Muslim, Southeast Asian), plus a length-matched neutral control, where a clinician verified that the gold answer remains invariant in all variants. We evaluate GPT-5.2, Llama-3.1-8B, DeepSeek-R1, and MedGemma (4B/27B) under option-only and brief-explanation prompting. Across models, cultural cues significantly affect accuracy (Cochran's Q, $p<10^-14$), with the largest degradation when identifier and context co-occur (up to 3-7 percentage points under option-only prompting), while neutral edits produce smaller, non-systematic changes. A human-validated rubric ($κ=0.76$) applied via an LLM-as-judge shows that more than half of culturally grounded explanations end in an incorrect answer, linking culture-referential reasoning to diagnostic failure. We release prompts and augmentations to support evaluation and mitigation of culturally induced diagnostic errors. |
| title | Counterfactual Cultural Cues Reduce Medical QA Accuracy in LLMs: Identifier vs Context Effects |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.20102 |