@inproceedings{hashiloni-etal-2025-dharmabench,
title = "{D}harma{B}ench: Evaluating Language Models on Buddhist Texts in {S}anskrit and {T}ibetan",
author = "Hashiloni, Kai Golan and
Cohen, Shay and
Shina, Asaf and
Yang, Jingyi and
Zwebner, Orr Meir and
Bajetta, Nicola and
Bilitski, Guy and
Sund{\'e}n, Rebecca and
Maduel, Guy and
Conlon, Ryan and
Barzilai, Ari and
Mass, Daniel and
Jia, Shanshan and
Naaman, Aviv and
Choden, Sonam and
Jamtsho, Sonam and
Qu, Yadi and
Isaacson, Harunaga and
Wangchuk, Dorji and
Fine, Shai and
Almogi, Orna and
Bar, Kfir",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.114/",
pages = "2088--2110",
ISBN = "979-8-89176-298-5",
abstract = "We assess the capabilities of large language models on tasks involving Buddhist texts written in Sanskrit and Classical Tibetan{---}two typologically distinct, low-resource historical languages. To this end, we introduce DharmaBench, a benchmark suite comprising 13 classification and detection tasks grounded in Buddhist textual traditions: six in Sanskrit and seven in Tibetan, with four shared across both. The tasks are curated from scratch, tailored to the linguistic and cultural characteristics of each language. We evaluate a range of models, from proprietary systems like GPT-4o to smaller, domain-specific open-weight models, analyzing their performance across tasks and languages. All datasets and code are publicly released, under the CC-BY-4 License and the Apache-2.0 License respectively, to support research on historical language processing and the development of culturally inclusive NLP systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hashiloni-etal-2025-dharmabench">
<titleInfo>
<title>DharmaBench: Evaluating Language Models on Buddhist Texts in Sanskrit and Tibetan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="given">Golan</namePart>
<namePart type="family">Hashiloni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asaf</namePart>
<namePart type="family">Shina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orr</namePart>
<namePart type="given">Meir</namePart>
<namePart type="family">Zwebner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Bajetta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Bilitski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sundén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Maduel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Conlon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="family">Barzilai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Mass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aviv</namePart>
<namePart type="family">Naaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonam</namePart>
<namePart type="family">Choden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonam</namePart>
<namePart type="family">Jamtsho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadi</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harunaga</namePart>
<namePart type="family">Isaacson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorji</namePart>
<namePart type="family">Wangchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Fine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orna</namePart>
<namePart type="family">Almogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>We assess the capabilities of large language models on tasks involving Buddhist texts written in Sanskrit and Classical Tibetan—two typologically distinct, low-resource historical languages. To this end, we introduce DharmaBench, a benchmark suite comprising 13 classification and detection tasks grounded in Buddhist textual traditions: six in Sanskrit and seven in Tibetan, with four shared across both. The tasks are curated from scratch, tailored to the linguistic and cultural characteristics of each language. We evaluate a range of models, from proprietary systems like GPT-4o to smaller, domain-specific open-weight models, analyzing their performance across tasks and languages. All datasets and code are publicly released, under the CC-BY-4 License and the Apache-2.0 License respectively, to support research on historical language processing and the development of culturally inclusive NLP systems.</abstract>
<identifier type="citekey">hashiloni-etal-2025-dharmabench</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.114/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>2088</start>
<end>2110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DharmaBench: Evaluating Language Models on Buddhist Texts in Sanskrit and Tibetan
%A Hashiloni, Kai Golan
%A Cohen, Shay
%A Shina, Asaf
%A Yang, Jingyi
%A Zwebner, Orr Meir
%A Bajetta, Nicola
%A Bilitski, Guy
%A Sundén, Rebecca
%A Maduel, Guy
%A Conlon, Ryan
%A Barzilai, Ari
%A Mass, Daniel
%A Jia, Shanshan
%A Naaman, Aviv
%A Choden, Sonam
%A Jamtsho, Sonam
%A Qu, Yadi
%A Isaacson, Harunaga
%A Wangchuk, Dorji
%A Fine, Shai
%A Almogi, Orna
%A Bar, Kfir
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F hashiloni-etal-2025-dharmabench
%X We assess the capabilities of large language models on tasks involving Buddhist texts written in Sanskrit and Classical Tibetan—two typologically distinct, low-resource historical languages. To this end, we introduce DharmaBench, a benchmark suite comprising 13 classification and detection tasks grounded in Buddhist textual traditions: six in Sanskrit and seven in Tibetan, with four shared across both. The tasks are curated from scratch, tailored to the linguistic and cultural characteristics of each language. We evaluate a range of models, from proprietary systems like GPT-4o to smaller, domain-specific open-weight models, analyzing their performance across tasks and languages. All datasets and code are publicly released, under the CC-BY-4 License and the Apache-2.0 License respectively, to support research on historical language processing and the development of culturally inclusive NLP systems.
%U https://aclanthology.org/2025.ijcnlp-long.114/
%P 2088-2110
Markdown (Informal)
[DharmaBench: Evaluating Language Models on Buddhist Texts in Sanskrit and Tibetan](https://aclanthology.org/2025.ijcnlp-long.114/) (Hashiloni et al., IJCNLP-AACL 2025)
ACL
- Kai Golan Hashiloni, Shay Cohen, Asaf Shina, Jingyi Yang, Orr Meir Zwebner, Nicola Bajetta, Guy Bilitski, Rebecca Sundén, Guy Maduel, Ryan Conlon, Ari Barzilai, Daniel Mass, Shanshan Jia, Aviv Naaman, Sonam Choden, Sonam Jamtsho, Yadi Qu, Harunaga Isaacson, Dorji Wangchuk, Shai Fine, Orna Almogi, and Kfir Bar. 2025. DharmaBench: Evaluating Language Models on Buddhist Texts in Sanskrit and Tibetan. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 2088–2110, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.