L3IA at AraSentEval 2026 Subtask 2: LLM-Based Multi-Step Pipeline for Arabic Sentiment Swap

Abdessamad Benlahbib, Hamza Alami, Mohamed M’haouach, Kaouthar Elyoussoufi


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.
Anthology ID:
2026.osact-1.37
Volume:
The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Hend Al-Khalifa, Mo El-Haj, Saad Ezzini
Venues:
OSACT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
274–277
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-osact-37
DOI:
10.63317/4wtc4onqmfgo
Bibkey:
Cite (ACL):
Abdessamad Benlahbib, Hamza Alami, Mohamed M’haouach, and Kaouthar Elyoussoufi. 2026. L3IA at AraSentEval 2026 Subtask 2: LLM-Based Multi-Step Pipeline for Arabic Sentiment Swap. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 274–277, Palma, Mallorca (Spain). Association for Computational Linguistics.
Cite (Informal):
L3IA at AraSentEval 2026 Subtask 2: LLM-Based Multi-Step Pipeline for Arabic Sentiment Swap (Benlahbib et al., OSACT 2026)
Copy Citation: