<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pulipaka-2026-psk">
    <titleInfo>
        <title>PSK@EEUCA 2026: Fine-tuning Large Language Models with Synthetic Data Augmentation for Multi-class Toxicity Detection in Gaming Chat</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Srikar</namePart>
        <namePart type="given">Kashyap</namePart>
        <namePart type="family">Pulipaka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ali</namePart>
            <namePart type="family">Hürriyetoğlu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hristo</namePart>
            <namePart type="family">Tanev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-402-6</identifier>
    </relatedItem>
    <abstract>This paper describes our system for the EEUCA 2026 Shared Task on Understanding Toxic Behavior in Gaming Communities. The task involves classifying World of Tanks chat messages into six toxicity categories: Non-toxic, Insults/Flaming, Other Offensive, Hate/Harassment, Threats, and Extremism. We explore multiple approaches including encoder-based models, instruction-tuned LLMs with LoRA fine-tuning, hierarchical classification, one-vs-rest strategies, and various ensemble methods. Our best system combines Llama 3.1 8B with carefully calibrated 5% synthetic data augmentation, achieving an F1-macro score of 0.6234 on the test set, placing 4th out of 35 participating teams. We provide extensive analysis of the dataset’s annotation patterns and their impact on model generalization, revealing a critical “validation trap” phenomenon where high validation performance correlates with poor test transfer.</abstract>
    <identifier type="citekey">pulipaka-2026-psk</identifier>
    <location>
        <url>https://aclanthology.org/2026.eeuca-1.21/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>192</start>
            <end>197</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PSK@EEUCA 2026: Fine-tuning Large Language Models with Synthetic Data Augmentation for Multi-class Toxicity Detection in Gaming Chat
%A Pulipaka, Srikar Kashyap
%Y Hürriyetoğlu, Ali
%Y Thapa, Surendrabikram
%Y Tanev, Hristo
%S Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-402-6
%F pulipaka-2026-psk
%X This paper describes our system for the EEUCA 2026 Shared Task on Understanding Toxic Behavior in Gaming Communities. The task involves classifying World of Tanks chat messages into six toxicity categories: Non-toxic, Insults/Flaming, Other Offensive, Hate/Harassment, Threats, and Extremism. We explore multiple approaches including encoder-based models, instruction-tuned LLMs with LoRA fine-tuning, hierarchical classification, one-vs-rest strategies, and various ensemble methods. Our best system combines Llama 3.1 8B with carefully calibrated 5% synthetic data augmentation, achieving an F1-macro score of 0.6234 on the test set, placing 4th out of 35 participating teams. We provide extensive analysis of the dataset’s annotation patterns and their impact on model generalization, revealing a critical “validation trap” phenomenon where high validation performance correlates with poor test transfer.
%U https://aclanthology.org/2026.eeuca-1.21/
%P 192-197

Markdown (Informal)

[PSK@EEUCA 2026: Fine-tuning Large Language Models with Synthetic Data Augmentation for Multi-class Toxicity Detection in Gaming Chat](https://aclanthology.org/2026.eeuca-1.21/) (Pulipaka, EEUCA 2026)

• PSK@EEUCA 2026: Fine-tuning Large Language Models with Synthetic Data Augmentation for Multi-class Toxicity Detection in Gaming Chat (Pulipaka, EEUCA 2026)

ACL

• Srikar Kashyap Pulipaka. 2026. PSK@EEUCA 2026: Fine-tuning Large Language Models with Synthetic Data Augmentation for Multi-class Toxicity Detection in Gaming Chat. In Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026), pages 192–197, San Diego, California, USA. Association for Computational Linguistics.