arXiv：cs.CL· Sravan Gorugantu, Mohd Nauman, Vijay Devane, Shyam Pawar, Viraj Thakur, Kundeshwar Pundalik, Piyush Sawarkar, Rohit Saluja, Maunendra Desarkar, Ganesh Ramakrishnan·· 3 小时前
AyurParam：面向阿育吠陀的双语领域专用语言模型
AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
AI 导读
研究团队发布 AyurParam-2.9B，一个从 Param-1-2.9B 微调而来的阿育吠陀领域双语语言模型，数据集涵盖古典文献与临床指南，包含英语和印地语的情境感知、推理及客观题问答。在 BhashaBench-Ayur 上，该模型超越同尺寸（1.5–3B 参数）所有开源指令微调模型，并与更大模型表现相当或更优。
正文
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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2511.02374 [cs.CL] |
| (or arXiv:2511.02374v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2511.02374 arXiv-issued DOI via DataCite |
Submission history
From: Kundeshwar Pundalik Mr [view email]
[v1]
Tue, 4 Nov 2025 08:53:21 UTC (455 KB)
[v2]
Thu, 8 Oct 2026 06:52:47 UTC (435 KB)
来源：arXiv：cs.CL · arxiv.org