Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911264464175104 |
|---|---|
| author | Abrar, Ajwad Oeshy, Nafisa Tabassum Maheru, Prianka Tabassum, Farzana Chowdhury, Tareque Mohmud |
| author_facet | Abrar, Ajwad Oeshy, Nafisa Tabassum Maheru, Prianka Tabassum, Farzana Chowdhury, Tareque Mohmud |
| contents | Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a framework that combines TextRank-based sentence extraction and medical named entity recognition with large language models (LLMs) to enhance faithfulness in medical text summarization. In our experiments, we fine-tuned the LLaMA-2-7B model on the MeQSum (English) and BanglaCHQ-Summ (Bangla) datasets, achieving consistent improvements across quality (ROUGE, BERTScore, readability) and faithfulness (SummaC, AlignScore) metrics, and outperforming zero-shot baselines and prior systems. Human evaluation further shows that over 80\% of generated summaries preserve critical medical information. These results highlight faithfulness as an essential dimension for reliable medical summarization and demonstrate the potential of our approach for safer deployment of LLMs in healthcare contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs Abrar, Ajwad Oeshy, Nafisa Tabassum Maheru, Prianka Tabassum, Farzana Chowdhury, Tareque Mohmud Computation and Language Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a framework that combines TextRank-based sentence extraction and medical named entity recognition with large language models (LLMs) to enhance faithfulness in medical text summarization. In our experiments, we fine-tuned the LLaMA-2-7B model on the MeQSum (English) and BanglaCHQ-Summ (Bangla) datasets, achieving consistent improvements across quality (ROUGE, BERTScore, readability) and faithfulness (SummaC, AlignScore) metrics, and outperforming zero-shot baselines and prior systems. Human evaluation further shows that over 80\% of generated summaries preserve critical medical information. These results highlight faithfulness as an essential dimension for reliable medical summarization and demonstrate the potential of our approach for safer deployment of LLMs in healthcare contexts. |
| title | Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.10768 |