大模型
arxiv.org ·
IndicParam：面向低资源印度语言的大模型评测基准
该论文提出 IndicParam，一个人工整理的基准，包含 13,000 多道多选题，覆盖 11 种低资源及极低资源印度语言（尼泊尔语、古吉拉特语、马拉地语、奥里亚语，以及多格里语、迈蒂利语、拉贾斯坦语、梵语、博多语、桑塔利语、孔卡尼语），另含梵语-英语混合语料。作者评测了 20 个闭源与开源模型，结果显示表现最好的 Gemini-2.5 平均准确率为 58%，GPT-5 为 45%，DeepSeek-3.2 为 43.1%。每道题被标注为知识型或纯语言型，以区分事实回忆与语法能力，并测试列表匹配、断言-理由、序列排序等题型。论文称该基准揭示了跨语言迁移的局限，数据集与评测脚本已公开。
AI推荐理由 arXiv 论文，摘要明确给出基准规模（13,000+ 道多选题、11 种语言）、评测模型数量（20 个）和具体准确率（Gemini-2.5 58%、GPT-5 45%、DeepSeek-3.2 43.1%），并区分知识型与语言型题目、覆盖多种题型，信息密度高、可验证。局限在于仅依据摘要，未提供数据集构建细节、标注一致性或基线复现结果，且低资源印度语言评测对多数开发者的直接落地价值有限。
72
正文
Computer Science > Computation and Language
arXiv:2512.00333 (cs)
[Submitted on 29 Nov 2025 (v1), last revised 12 Jan 2026 (this version, v2)]
Title:IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages
Authors:Ayush Maheshwari, Kaushal Sharma, Vivek Patel, Aditya Maheshwari
View a PDF of the paper titled IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages, by Ayush Maheshwari and 3 other authors
View PDF
HTML (experimental)
Abstract:While large language models excel on high-resource multilingual tasks, low- and extremely low-resource Indic languages remain severely under-evaluated. We present IndicParam, a human-curated benchmark of over 13,000 multiple-choice questions covering 11 such languages (Nepali, Gujarati, Marathi, Odia as low-resource; Dogri, Maithili, Rajasthani, Sanskrit, Bodo, Santali, Konkani as extremely low-resource) plus Sanskrit-English code-mixed set. We evaluated 20 LLMs, both proprietary and open-weights, which reveals that even the top-performing \texttt{Gemini-2.5} reaches 58\% average accuracy, followed by \texttt{GPT-5} (45) and \texttt{DeepSeek-3.2} (43.1). We additionally label each question as knowledge-oriented or purely linguistic to discriminate factual recall from grammatical proficiency. Further, we assess the ability of LLMs to handle diverse question formats-such as list-based matching, assertion-reason pairs, and sequence ordering-alongside conventional multiple-choice questions. \benchmark\ provides insights into limitations of cross-lingual transfer and establishes a challenging benchmark for Indic languages. The dataset is available at this https URL. Scripts to run benchmark are present at this https URL.
Subjects:
Computation and Language (cs.CL)
Cite as:
arXiv:2512.00333 [cs.CL]
(or
arXiv:2512.00333v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2512.00333
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Ayush Maheshwari Dr. [view email]
[v1]
Sat, 29 Nov 2025 05:49:50 UTC (1,442 KB)
[v2]
Mon, 12 Jan 2026 13:16:09 UTC (1,464 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages, by Ayush Maheshwari and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2025-12
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
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.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)