{"ID":5937253,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T05:27:20.080601477Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04690","arxiv_id":"2607.04690","title":"PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection","abstract":"We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We redefine stance as cloze-style masked language modeling (MLM), letting a verbalizer map label words to stance categories through the pre-trained MLM head rather than appending a randomly initialized classification head. We complement this with prototypical contrastive learning, which uses learnable class prototypes for batch-size independent contrastive training, and topic-conditional layer normalization for cross-topic Arabic stance detection. PAST-TIDE achieves macro-F1 scores of 0.75 for Subtask A and 0.74 for Subtask B on the official leaderboard, indicating that minimal architectural additions to a pre-trained model can remain competitive in low-resource settings.","short_abstract":"We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We redefine stance as cloze-style masked language modeling (MLM), letting a verbalizer map label words to stance categories through the pre-trained...","url_abs":"https://arxiv.org/abs/2607.04690","url_pdf":"https://arxiv.org/pdf/2607.04690v1","authors":"[\"Md. Shakhoyat Rahman Shujon\",\"MD Jahid Hasan Jim\",\"Md. Milon Islam\",\"Md Rezwanul Haque\",\"Fakhri Karray\"]","published":"2026-07-06T05:33:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}