@inproceedings{ahmad-etal-2025-bncontextqa,
title = "bn{C}ontext{QA}: Benchmarking Long-Context Question Answering and Challenges in {B}angla",
author = "Ahmad, Adnan and
Adiba, Labiba and
Rasul, Namirah and
Laskar, Md Tahmid Rahman and
Ahmed, Sabbir",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Hassan, Naeemul and
Prince, Enamul Hoque and
Tasnim, Mohiuddin and
Rony, Md Rashad Al Hasan and
Rahman, Md Tahmid Rahman",
booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.banglalp-1.29/",
pages = "357--365",
ISBN = "979-8-89176-314-2",
abstract = "Large models have advanced in processing long input sequences, but their ability to consistently use information across extended contexts remains a challenge. Recent studies highlight a positional bias where models prioritize information at the beginning or end of the input while neglecting the middle, resulting in a U-shaped performance curve but this was limited to English. Whether this bias is universal or shaped by language-specific factors remains unclear. In this work, we investigate positional bias in Bangla, a widely spoken but computationally underrepresented language. To support this, we introduce a novel Bangla benchmark dataset, bnContextQA, specifically designed for long-context comprehension. The dataset comprises of 350 long-context QA instances, each paired with 30 context paragraphs, allowing controlled evaluation of information retrieval at different positions. Using this dataset, we assess the performance of LLMs on Bangla across varying passage positions, providing insights into cross-linguistic positional effects. The bnContextQA dataset is publicly available at https://github.com/labiba02/bnContextQA.git to support future research on long-context understanding in Bangla and multilingual LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmad-etal-2025-bncontextqa">
<titleInfo>
<title>bnContextQA: Benchmarking Long-Context Question Answering and Challenges in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adnan</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Labiba</namePart>
<namePart type="family">Adiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Namirah</namePart>
<namePart type="family">Rasul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabbir</namePart>
<namePart type="family">Ahmed</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 Second Workshop on Bangla Language Processing (BLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naeemul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="given">Hoque</namePart>
<namePart type="family">Prince</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohiuddin</namePart>
<namePart type="family">Tasnim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rashad</namePart>
<namePart type="given">Al</namePart>
<namePart type="given">Hasan</namePart>
<namePart type="family">Rony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-314-2</identifier>
</relatedItem>
<abstract>Large models have advanced in processing long input sequences, but their ability to consistently use information across extended contexts remains a challenge. Recent studies highlight a positional bias where models prioritize information at the beginning or end of the input while neglecting the middle, resulting in a U-shaped performance curve but this was limited to English. Whether this bias is universal or shaped by language-specific factors remains unclear. In this work, we investigate positional bias in Bangla, a widely spoken but computationally underrepresented language. To support this, we introduce a novel Bangla benchmark dataset, bnContextQA, specifically designed for long-context comprehension. The dataset comprises of 350 long-context QA instances, each paired with 30 context paragraphs, allowing controlled evaluation of information retrieval at different positions. Using this dataset, we assess the performance of LLMs on Bangla across varying passage positions, providing insights into cross-linguistic positional effects. The bnContextQA dataset is publicly available at https://github.com/labiba02/bnContextQA.git to support future research on long-context understanding in Bangla and multilingual LLMs.</abstract>
<identifier type="citekey">ahmad-etal-2025-bncontextqa</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.29/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>357</start>
<end>365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T bnContextQA: Benchmarking Long-Context Question Answering and Challenges in Bangla
%A Ahmad, Adnan
%A Adiba, Labiba
%A Rasul, Namirah
%A Laskar, Md Tahmid Rahman
%A Ahmed, Sabbir
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Prince, Enamul Hoque
%Y Tasnim, Mohiuddin
%Y Rony, Md Rashad Al Hasan
%Y Rahman, Md Tahmid Rahman
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F ahmad-etal-2025-bncontextqa
%X Large models have advanced in processing long input sequences, but their ability to consistently use information across extended contexts remains a challenge. Recent studies highlight a positional bias where models prioritize information at the beginning or end of the input while neglecting the middle, resulting in a U-shaped performance curve but this was limited to English. Whether this bias is universal or shaped by language-specific factors remains unclear. In this work, we investigate positional bias in Bangla, a widely spoken but computationally underrepresented language. To support this, we introduce a novel Bangla benchmark dataset, bnContextQA, specifically designed for long-context comprehension. The dataset comprises of 350 long-context QA instances, each paired with 30 context paragraphs, allowing controlled evaluation of information retrieval at different positions. Using this dataset, we assess the performance of LLMs on Bangla across varying passage positions, providing insights into cross-linguistic positional effects. The bnContextQA dataset is publicly available at https://github.com/labiba02/bnContextQA.git to support future research on long-context understanding in Bangla and multilingual LLMs.
%U https://aclanthology.org/2025.banglalp-1.29/
%P 357-365
Markdown (Informal)
[bnContextQA: Benchmarking Long-Context Question Answering and Challenges in Bangla](https://aclanthology.org/2025.banglalp-1.29/) (Ahmad et al., BanglaLP 2025)
ACL