aiqbench analysis
This paper presents AyurParam, a 2.9B parameter bilingual model fine-tuned specifically for the specialized domain of Ayurveda to address mainstream LLMs' failure in handling culturally nuanced medical knowledge. By leveraging an expertly curated dataset of classical texts and clinical guidance, the model demonstrates that high-quality supervision and authentic domain adaptation can yield superior performance over larger, general-purpose counterparts in niche applications. This work underscores the critical need for targeted fine-tuning strategies to ensure factual precision and cultural congruence in AI systems dealing with traditional medical systems.
AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
arXiv:2511.02374v2 Announce Type: replace-cross Abstract: Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cultural, linguistic, and subject-matter expertise. In particular, traditional medical systems such as Ayurveda embody centuries of nuanced textual and clinical knowledge that mainstream LLMs fail to accurately interpret or apply. We introduce AyurParam-2.9B, a domain-specialized, bilingual language model fine-tuned from Param-1-2.9B using an extensive, expertly curated Ayurveda dataset spanning classical texts and clinical guidance. AyurParam's dataset incorporates context-aware, reasoning, and objective-style Q&A in both English and Hindi, with rigorous annotation protocols for factual precision and instructional clarity. Benchmarked on BhashaBench-Ayur, AyurParam not only surpasses all open-source instruction-tuned models in its size class (1.5--3B parameters), but also demonstrates competitive or superior performance compared to much larger models. The results from AyurParam highlight the necessity for authentic domain adaptation and high-quality supervision in delivering reliable, culturally congruent AI for specialized medical knowledge.
Abstract:Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cultural, linguistic, and subject-matter expertise. In particular, traditional medical systems such as Ayurveda embody centuries of nuanced textual and clinical knowledge that mainstream LLMs fail to accurately interpret or apply. We introduce AyurParam-2.9B, a domain-specialized, bilingual language model fine-tuned from Param-1-2.9B using an extensive, expertly curated Ayurveda dataset spanning classical texts and clinical guidance. AyurParam's dataset incorporates context-aware, reasoning, and objective-style Q&A in both English and Hindi, with rigorous annotation protocols for factual precision and instructional clarity. Benchmarked on BhashaBench-Ayur, AyurParam not only surpasses all open-source instruction-tuned models in its size class (1.5--3B parameters), but also demonstrates competitive or superior performance compared to much larger models. The results from AyurParam highlight the necessity for authentic domain adaptation and high-quality supervision in delivering reliable, culturally congruent AI for specialized medical knowledge.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2511.02374 [cs.CL]
(or arXiv:2511.02374v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2511.02374 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 247 words
Related coverage
Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations
arXiv · Aug 28, 2026
Meet Cohere Transcribe Arabic
Cohere · Jul 7, 2026
Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models
arXiv · Jun 6, 2026
Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions
arXiv · Jun 17, 2026