@inproceedings{ralethe-buys-2025-kerlqa,
title = "{KERLQA}: Knowledge-Enhanced Reinforcement Learning for Question Answering in Low-resource Languages",
author = "Ralethe, Sello and
Buys, Jan",
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.99/",
pages = "1834--1846",
ISBN = "979-8-89176-298-5",
abstract = "Question answering in low-resource languages faces critical challenges when models encounter questions beyond their knowledge boundaries, often producing confident but incorrect answers. We propose Knowledge-Enhanced Reinforcement Learning for Question Answering (KERLQA), a novel approach that combines knowledge graph integration with reinforcement learning to enable principled abstention decisions. Unlike existing refusal-tuned methods that make binary decisions based solely on internal confidence, KERLQA implements a three-way decision process: answer with internal knowledge, answer with external knowledge assistance, or abstain. Using a composite reward function that jointly optimizes for correctness, appropriate abstention, and efficient knowledge utilization, we train policies via PPO and DPO with dynamic calibration for low-resource settings. Experiments on CommonsenseQA and OpenBookQA across English and four South African languages show KERLQA achieves improved F1 scores, with up to 6.2 point improvements in low-resource languages. Our analysis reveals that KERLQA reduces false positive abstention rates by 30{\%} while expanding the boundary of answerable questions through external knowledge integration."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ralethe-buys-2025-kerlqa">
<titleInfo>
<title>KERLQA: Knowledge-Enhanced Reinforcement Learning for Question Answering in Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sello</namePart>
<namePart type="family">Ralethe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Buys</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>Question answering in low-resource languages faces critical challenges when models encounter questions beyond their knowledge boundaries, often producing confident but incorrect answers. We propose Knowledge-Enhanced Reinforcement Learning for Question Answering (KERLQA), a novel approach that combines knowledge graph integration with reinforcement learning to enable principled abstention decisions. Unlike existing refusal-tuned methods that make binary decisions based solely on internal confidence, KERLQA implements a three-way decision process: answer with internal knowledge, answer with external knowledge assistance, or abstain. Using a composite reward function that jointly optimizes for correctness, appropriate abstention, and efficient knowledge utilization, we train policies via PPO and DPO with dynamic calibration for low-resource settings. Experiments on CommonsenseQA and OpenBookQA across English and four South African languages show KERLQA achieves improved F1 scores, with up to 6.2 point improvements in low-resource languages. Our analysis reveals that KERLQA reduces false positive abstention rates by 30% while expanding the boundary of answerable questions through external knowledge integration.</abstract>
<identifier type="citekey">ralethe-buys-2025-kerlqa</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.99/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1834</start>
<end>1846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KERLQA: Knowledge-Enhanced Reinforcement Learning for Question Answering in Low-resource Languages
%A Ralethe, Sello
%A Buys, Jan
%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 ralethe-buys-2025-kerlqa
%X Question answering in low-resource languages faces critical challenges when models encounter questions beyond their knowledge boundaries, often producing confident but incorrect answers. We propose Knowledge-Enhanced Reinforcement Learning for Question Answering (KERLQA), a novel approach that combines knowledge graph integration with reinforcement learning to enable principled abstention decisions. Unlike existing refusal-tuned methods that make binary decisions based solely on internal confidence, KERLQA implements a three-way decision process: answer with internal knowledge, answer with external knowledge assistance, or abstain. Using a composite reward function that jointly optimizes for correctness, appropriate abstention, and efficient knowledge utilization, we train policies via PPO and DPO with dynamic calibration for low-resource settings. Experiments on CommonsenseQA and OpenBookQA across English and four South African languages show KERLQA achieves improved F1 scores, with up to 6.2 point improvements in low-resource languages. Our analysis reveals that KERLQA reduces false positive abstention rates by 30% while expanding the boundary of answerable questions through external knowledge integration.
%U https://aclanthology.org/2025.ijcnlp-long.99/
%P 1834-1846
Markdown (Informal)
[KERLQA: Knowledge-Enhanced Reinforcement Learning for Question Answering in Low-resource Languages](https://aclanthology.org/2025.ijcnlp-long.99/) (Ralethe & Buys, IJCNLP-AACL 2025)
ACL