@inproceedings{krubhakaran-etal-2026-vitech,
    title = "{VITECH}@{D}ravidian{L}ang{T}ech2026: Prompting and {L}o{RA} Adaptation for {T}amil Abusive Language Detection - A Comparative Study of Open {LLM}s",
    author = "Krubhakaran, Triambiga  and
      B, Senthil Kumar  and
      Nagarajan, Kaviya  and
      N, Balaji",
    editor = "Chakravarthi, Bharathi Raja  and
      Priyadharshini, Ruba  and
      Madasamy, Anand Kumar  and
      Thavareesan, Sajeetha  and
      Rajiakodi, Saranya  and
      Navaneethakrishnan, Subalalitha  and
      Chinnappa, Dhivya  and
      Palani, Balasubramanian  and
      Subramanian, Malliga  and
      Shanmugavadivel, Kogilavani  and
      Rajalakshmi, Ratnavel",
    booktitle = "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for {D}ravidian Languages",
    month = jul,
    year = "2026",
    address = "Underline (Virtual)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.dravidianlangtech-1.69/",
    pages = "436--441",
    ISBN = "979-8-89176-401-9",
    abstract = "The detection of abusive Tamil text using large language models (LLMs) has received relatively little attention compared to BERT variations. We empirically evaluated four families of open-weight LLMs {---}Gemma, LLaMA, Qwen, and DeepSeek-Distilled{---} on the Tamil dataset provided by the shared task. The models are assessed under two in-context learning settings (zero-shot and few-shot) and a parameter-efficient fine-tuning approach using LoRA, with model sizes of approximately 2B and 8B parameters. Experimental results show that 8B models consistently outperform their 2B counterparts, indicating the benefit of increased model capacity. Among the adaptation techniques, LoRA fine-tuning significantly outperforms both zero-shot and few-shot prompting. Across all evaluated settings, Google{'}s Gemma-2-9B model with LoRA fine-tuning achieved the best performance compared to the other model families and our test result was ranked 12th among all 22 submissions with the 0.7959 f1-score."
}