Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation
Quick Answer
This paper shows that A new severity-aware multi-model framework for medical text generation improves response quality by using a three-stage curriculum learning strategy.
Quick Take
Trained on the MAQA dataset, it achieves BERTScore results of 86.71% and 90.30% after fine-tuning, outperforming baseline models.
Key Points
- Introduces a severity-aware framework for medical text generation.
- Employs a three-stage curriculum learning strategy for model training.
- Utilizes five for generating candidate responses.
- Achieves BERTScore of 90.30% after fine-tuning on the MAQA dataset.
- Improves response relevance and quality in telehealth systems.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 05510v1 Announce Type: new Abstract: Telehealth systems have become increasingly important for delivering accessible and timely medical information. Existing often struggle to provide consistent and contextually appropriate medical responses across varying levels of case severity. This limitation highlights the need for models that can effectively adapt to the progressive complexity in medical queries.
To address this challenge, we introduce a severity-aware multi-model framework that integrates curriculum training strategy with relevance-based response selection. The proposed framework employs a three-stage curriculum learning strategy, where each model is trained sequentially on mild, moderate, and critical cases to progressively acquire domain knowledge. The approach utilizes five large language models, each independently trained under the same curriculum scheme.
During inference, all models generate candidate responses, and the most appropriate response is selected as the final output. The framework is trained and evaluated on the MAQA dataset, which provides annotated medical question-answer pairs. Experimental results evaluated using BERTScore demonstrate that the proposed method achieves superior performance compared to both baseline and fine-tuned models, attaining 86. 71% in the baseline setting and 90. 30% after fine-tuning.
These results highlight the effectiveness of combining curriculum learning with multi-model response selection in improving response quality and relevance in medical text generation.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.