Multi-LLM Collaboration for Medication Recommendation
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_ | 1866912749648347136 |
|---|---|
| author | Sanchez, Huascar Hitaj, Briland Bergmann, Jules Briesemeister, Linda |
| author_facet | Sanchez, Huascar Hitaj, Briland Bergmann, Jules Briesemeister, Linda |
| contents | As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challenge. Individual large language models (LLMs) are susceptible to hallucinations and inconsistency, whereas naive ensembles of models often fail to deliver stable and credible recommendations. Building on our previous work on LLM Chemistry, which quantifies the collaborative compatibility among LLMs, we apply this framework to improve the reliability in medication recommendation from brief clinical vignettes. Our approach leverages multi-LLM collaboration guided by Chemistry-inspired interaction modeling, enabling ensembles that are effective (exploiting complementary strengths), stable (producing consistent quality), and calibrated (minimizing interference and error amplification). We evaluate our Chemistry-based Multi-LLM collaboration strategy on real-world clinical scenarios to investigate whether such interaction-aware ensembles can generate credible, patient-specific medication recommendations. Preliminary results are encouraging, suggesting that LLM Chemistry-guided collaboration may offer a promising path toward reliable and trustworthy AI assistants in clinical practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-LLM Collaboration for Medication Recommendation Sanchez, Huascar Hitaj, Briland Bergmann, Jules Briesemeister, Linda Machine Learning Artificial Intelligence Computation and Language As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challenge. Individual large language models (LLMs) are susceptible to hallucinations and inconsistency, whereas naive ensembles of models often fail to deliver stable and credible recommendations. Building on our previous work on LLM Chemistry, which quantifies the collaborative compatibility among LLMs, we apply this framework to improve the reliability in medication recommendation from brief clinical vignettes. Our approach leverages multi-LLM collaboration guided by Chemistry-inspired interaction modeling, enabling ensembles that are effective (exploiting complementary strengths), stable (producing consistent quality), and calibrated (minimizing interference and error amplification). We evaluate our Chemistry-based Multi-LLM collaboration strategy on real-world clinical scenarios to investigate whether such interaction-aware ensembles can generate credible, patient-specific medication recommendations. Preliminary results are encouraging, suggesting that LLM Chemistry-guided collaboration may offer a promising path toward reliable and trustworthy AI assistants in clinical practice. |
| title | Multi-LLM Collaboration for Medication Recommendation |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2512.05066 |