@inproceedings{benlahbib-etal-2026-l3ia,
    title = "{L}3{IA} at {A}ra{S}ent{E}val 2026 Subtask 2: {LLM}-Based Multi-Step Pipeline for {A}rabic Sentiment Swap",
    author = "Benlahbib, Abdessamad  and
      Alami, Hamza  and
      M{'}haouach, Mohamed  and
      Elyoussoufi, Kaouthar",
    editor = "Al-Khalifa, Hend  and
      El-Haj, Mo  and
      Ezzini, Saad",
    booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.osact-1.37/",
    doi = "10.63317/4wtc4onqmfgo",
    pages = "274--277",
    abstract = "This paper describes our system submitted to the AraSentEval 2026 Shared Task, Subtask 2: Arabic Sentiment Swap. The task requires rewriting Arabic sentences to invert their sentiment polarity while preserving the core meaning. We propose a multi-step pipeline approach that uses large language models (LLMs). Our method decomposes the sentiment inversion problem into three stages: (1) sentiment expression extraction, where the model identifies all sentiment-bearing words and phrases in the input sentence; (2) opposite expression generation, where each identified expression is replaced by its semantic opposite; and (3) sentence reconstruction, where the final output is assembled to ensure grammatical correctness and natural fluency. Our system achieves 74.3{\%} sentiment style accuracy, 27.22 BLEU, and 55.04 chrF on the official test set."
}