Unverified50% confidenceFactExact time
An empirical study of real users in four countries—India, Nigeria, Brazil, and Pakistan—evaluated the safety of large language models in health scenarios, using real conversation data with age and gender.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe study advocates that robust accent classification evaluation should incorporate both speaker-isolated evaluation and cross-corpus testing.61% similarUnverifiedPTC-Bias current experiments are primarily based on the English LibriSpeech dataset and specific SpeechLLMs; its performance in other languages such as Chinese, real noisy environments, and larger bias word lists remains to be validated.59% similarUnverifiedA study systematically compared two categories of data augmentation approaches across four low-resource languages plus English and five different data scales, with analysis carried down to the phoneme level.59% similarUnverifiedThe study evaluated 16 large language models as well as a control group of 60 licensed practitioners of traditional Chinese medicine.59% similarUnverifiedThe study uses L2-ARCTIC and multiple external English accent datasets to compare two evaluation settings: file-level splitting and speaker-isolated splitting.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023651API
curl https://kongchang.com/api/v1/knowledge/claims/1023651MCP
get_claim(id=1023651)