@inproceedings{riahi-samani-etal-2025-large,
title = "Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection",
author = "Riahi Samani, Ali and
Wang, Tianhao and
Li, Kangshuo and
Chen, Feng",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.416/",
pages = "6230--6243",
abstract = "Recent advancements in natural language processing, driven by Large Language Models (LLMs), have significantly improved text comprehension, enabling these models to handle complex tasks with greater efficiency. A key feature of LLMs is their ability to engage in contextual learning, which allows them to understand and apply instructions given in natural language to new scenarios without requiring additional training. This capability is particularly valuable in social media, where LLMs can be crucial in addressing challenges in explainable sexism detection. We hypothesize that by leveraging contextual learning capabilities, LLMs can provide clear, explainable insights into why certain content is flagged as problematic, thus enhancing transparency in the sexism detection process. To this end, we propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection. We studied two well-known LLMs, Mistral-7B and LLaMA-3-8B, in zero-shot, supervised fine-tuning, and RLHF scenarios to conclude the superior ability of LLMs in sexism detection. The experimental results reported in this work, based on three tasks of Explainable Detection of Online Sexism (EDOS), highlight the importance of RLHF for building explainable systems in online discourse. Furthermore, we found that the LLaMA-3-8B model achieves the best results using the RLHF approach, scoring 0.8681 on Task A (binary sexism detection), 0.6829 on Task B (category classification of sexism), and 0.4722 on Task C (fine-grained sexism vectors) test sets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riahi-samani-etal-2025-large">
<titleInfo>
<title>Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Riahi Samani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kangshuo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in natural language processing, driven by Large Language Models (LLMs), have significantly improved text comprehension, enabling these models to handle complex tasks with greater efficiency. A key feature of LLMs is their ability to engage in contextual learning, which allows them to understand and apply instructions given in natural language to new scenarios without requiring additional training. This capability is particularly valuable in social media, where LLMs can be crucial in addressing challenges in explainable sexism detection. We hypothesize that by leveraging contextual learning capabilities, LLMs can provide clear, explainable insights into why certain content is flagged as problematic, thus enhancing transparency in the sexism detection process. To this end, we propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection. We studied two well-known LLMs, Mistral-7B and LLaMA-3-8B, in zero-shot, supervised fine-tuning, and RLHF scenarios to conclude the superior ability of LLMs in sexism detection. The experimental results reported in this work, based on three tasks of Explainable Detection of Online Sexism (EDOS), highlight the importance of RLHF for building explainable systems in online discourse. Furthermore, we found that the LLaMA-3-8B model achieves the best results using the RLHF approach, scoring 0.8681 on Task A (binary sexism detection), 0.6829 on Task B (category classification of sexism), and 0.4722 on Task C (fine-grained sexism vectors) test sets.</abstract>
<identifier type="citekey">riahi-samani-etal-2025-large</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.416/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>6230</start>
<end>6243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection
%A Riahi Samani, Ali
%A Wang, Tianhao
%A Li, Kangshuo
%A Chen, Feng
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F riahi-samani-etal-2025-large
%X Recent advancements in natural language processing, driven by Large Language Models (LLMs), have significantly improved text comprehension, enabling these models to handle complex tasks with greater efficiency. A key feature of LLMs is their ability to engage in contextual learning, which allows them to understand and apply instructions given in natural language to new scenarios without requiring additional training. This capability is particularly valuable in social media, where LLMs can be crucial in addressing challenges in explainable sexism detection. We hypothesize that by leveraging contextual learning capabilities, LLMs can provide clear, explainable insights into why certain content is flagged as problematic, thus enhancing transparency in the sexism detection process. To this end, we propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection. We studied two well-known LLMs, Mistral-7B and LLaMA-3-8B, in zero-shot, supervised fine-tuning, and RLHF scenarios to conclude the superior ability of LLMs in sexism detection. The experimental results reported in this work, based on three tasks of Explainable Detection of Online Sexism (EDOS), highlight the importance of RLHF for building explainable systems in online discourse. Furthermore, we found that the LLaMA-3-8B model achieves the best results using the RLHF approach, scoring 0.8681 on Task A (binary sexism detection), 0.6829 on Task B (category classification of sexism), and 0.4722 on Task C (fine-grained sexism vectors) test sets.
%U https://aclanthology.org/2025.coling-main.416/
%P 6230-6243
Markdown (Informal)
[Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection](https://aclanthology.org/2025.coling-main.416/) (Riahi Samani et al., COLING 2025)
ACL