Papers by Pengyuan Li
Don’t be my Doctor! Recognizing Healthcare Advice in Large Language Models (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are becoming increasingly popular in everyday use, especially in highly regulated domains such as healthcare, where misleading advice may influence users to commit malpractice. |
| Approach: | They present a large-scale health-advice benchmark dataset that evaluates large language models' ability to recognize health-related advice in industrial settings. |
| Outcome: | The proposed model can be misinterpreted as direct advice in highly regulated domains such as healthcare, but the results are not enough to protect them from misinterpreting them as medical advice. |
CLGC: A Corpus for Chinese Literary Grace Evaluation (2022.lrec-1)
Copied to clipboard
| Challenge: | Literature grace is a key element of the style and quality of articles in China. |
| Approach: | They propose to annotate a Chinese literary grace corpus with 10,000 texts and 1.85 million tokens and build a literary grace evaluation task to assess the literary grace level. |
| Outcome: | The proposed model achieves 79.71% on the weighted average F1-score. |