@inproceedings{karki-etal-2026-shrinep,
    title = "{S}hri{N}ep@{EEUCA} 2026: {RAKSHAK} {--} Multi-Task {D}e{BERT}a with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification",
    author = "Karki, Binayak  and
      Kafle, Aryan  and
      Ghimire, Pingala",
    editor = {H{\"u}rriyeto{\u{g}}lu, Ali  and
      Thapa, Surendrabikram  and
      Tanev, Hristo},
    booktitle = "Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications ({EEUCA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.eeuca-1.19/",
    pages = "177--184",
    ISBN = "979-8-89176-402-6",
    abstract = "This paper presents two systems for the GameTox Shared Task at the Workshop on EEUCA at ACL 2026, which requires classifying World of Tanks chat utterances into six fine-grained toxic intent categories (Labels 0{--}5). Severe class imbalance, domain-specific multilingual slang, and extremely scarce data for rare categories such as Threats (Label 4, 60 samples) and Extremism (Label 5, 24 samples) make this a challenging classification problem. Our primary submission, RAKSHAK (rakṣaka, Sanskrit for ``Protector''), is a multi-task DeBERTa-v3-base framework combining rationale distillation from Qwen2.5-14B, Supervised Contrastive Loss, and dedicated rare-class binary heads. RAKSHAK{'}s training data is augmented with cross-domain transfer from the Jigsaw Toxic Comment dataset (16,225 samples mapped to Labels 1{--}4) and 100 LLM-generated extremism samples for Label 5. Our secondary system (M1) fine-tunes DeBERTa-v3-base with Focal Loss on the original GameTox data plus the same 100 extremism samples, without Jigsaw transfer. RAKSHAK achieves a Macro F1 of 0.5883 on the official test set, ranking 7th out of 35 participating teams, while M1 achieves 0.5252 Macro F1. An ablation comparing M1 with and without Jigsaw data shows that cross-domain transfer accounts for +2.6 F1 points, while RAKSHAK{'}s multi-task architecture contributes a further +3.7 points."
}