@inproceedings{saha-etal-2025-benchmarking,
title = "Benchmarking {B}angla Causality: A Dataset of Implicit and Explicit Causal Sentences and Cause-Effect Relations",
author = "Saha, Diya and
Jana, Sudeshna and
Sinha, Manjira and
Dasgupta, Tirthankar",
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.findings-ijcnlp.46/",
pages = "786--794",
ISBN = "979-8-89176-303-6",
abstract = "Causal reasoning is central to language understanding, yet remains under-resourced in Bangla. In this paper, we introduce the first large-scale dataset for causal inference in Bangla, consisting of over 11663 sentences annotated for causal sentence types (explicit, implicit, non-causal) and token-level spans for causes, effects, and connectives. The dataset captures both simple and complex causal structures across diverse domains such as news, education, and health. We further benchmark a suite of state-of-the-art instruction-tuned large language models, including LLaMA 3.3 70B, Gemma 2 9B, Qwen 32B, and DeepSeek, under zero-shot and three-shot prompting conditions. Our analysis reveals that while LLMs demonstrate moderate success in explicit causality detection, their performance drops significantly on implicit and span-level extraction tasks. This work establishes a foundational resource for Bangla causal understanding and highlights key challenges in adapting multilingual LLMs for structured reasoning in low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-etal-2025-benchmarking">
<titleInfo>
<title>Benchmarking Bangla Causality: A Dataset of Implicit and Explicit Causal Sentences and Cause-Effect Relations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diya</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudeshna</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manjira</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</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">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Causal reasoning is central to language understanding, yet remains under-resourced in Bangla. In this paper, we introduce the first large-scale dataset for causal inference in Bangla, consisting of over 11663 sentences annotated for causal sentence types (explicit, implicit, non-causal) and token-level spans for causes, effects, and connectives. The dataset captures both simple and complex causal structures across diverse domains such as news, education, and health. We further benchmark a suite of state-of-the-art instruction-tuned large language models, including LLaMA 3.3 70B, Gemma 2 9B, Qwen 32B, and DeepSeek, under zero-shot and three-shot prompting conditions. Our analysis reveals that while LLMs demonstrate moderate success in explicit causality detection, their performance drops significantly on implicit and span-level extraction tasks. This work establishes a foundational resource for Bangla causal understanding and highlights key challenges in adapting multilingual LLMs for structured reasoning in low-resource languages.</abstract>
<identifier type="citekey">saha-etal-2025-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.46/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>786</start>
<end>794</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Bangla Causality: A Dataset of Implicit and Explicit Causal Sentences and Cause-Effect Relations
%A Saha, Diya
%A Jana, Sudeshna
%A Sinha, Manjira
%A Dasgupta, Tirthankar
%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
%@ 979-8-89176-303-6
%F saha-etal-2025-benchmarking
%X Causal reasoning is central to language understanding, yet remains under-resourced in Bangla. In this paper, we introduce the first large-scale dataset for causal inference in Bangla, consisting of over 11663 sentences annotated for causal sentence types (explicit, implicit, non-causal) and token-level spans for causes, effects, and connectives. The dataset captures both simple and complex causal structures across diverse domains such as news, education, and health. We further benchmark a suite of state-of-the-art instruction-tuned large language models, including LLaMA 3.3 70B, Gemma 2 9B, Qwen 32B, and DeepSeek, under zero-shot and three-shot prompting conditions. Our analysis reveals that while LLMs demonstrate moderate success in explicit causality detection, their performance drops significantly on implicit and span-level extraction tasks. This work establishes a foundational resource for Bangla causal understanding and highlights key challenges in adapting multilingual LLMs for structured reasoning in low-resource languages.
%U https://aclanthology.org/2025.findings-ijcnlp.46/
%P 786-794
Markdown (Informal)
[Benchmarking Bangla Causality: A Dataset of Implicit and Explicit Causal Sentences and Cause-Effect Relations](https://aclanthology.org/2025.findings-ijcnlp.46/) (Saha et al., Findings 2025)
ACL