, mai 2026 — « Role-adapted clinical report generation for ultrasound measurements in low-resource settings » in Proceedings of the 8th workshop on clinical natural language processing (clinical NLP) @ LREC 2026.. , , p. 262-269 tex.hal_id: hal-05669630 tex.hal_version: v1
, janvier 2026 — Fine-Tuning Language Models for Structured Botanical Trait Extraction and Species Comparison. As artificial intelligence (AI) becomes central to biodiversity research, transforming morphological descriptions of species… Biodiversity Information Science and Standards vol. 10, , e183035 ISBN: 2535-0897 Type: 10.3897/biss.10.183035
, janvier 2026 — Fine-tuning language models for structured botanical trait extraction and species comparison. Biodiversity Information Science and Standards vol. 10, , e183035 tex.hal_id: hal-05468241 tex.hal_version: v1
, septembre 2025 — « F-LoRA-QA: Finetuning LLaMA Models with Low-Rank Adaptation for French Botanical Question Generation and Answering » in International Conference Recent Advances in Natural Language Processing (RANLP 2025).. Despite recent advances in large language models (LLMs), most question-answering (QA) systems remain English-centric and poorly… , , p. 787-796 Type: 10.26615/978-954-452-098-4-091
ISBN
978-954-452-098-4
, septembre 2025 — « Beyond BLEU: Ethical Risks of Misleading Evaluation in Domain-Specific QA with LLMs » in Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models associated with RANLP 2025.. Large Language Models (LLMs) are increasingly used in scientific question answering (QA), including high-stakes fields such as… , , p. 77-86 Type: 10.26615/978-954-452-102-8_009
ISBN
978-954-452-102-8
, août 2024 — FloraNER: A new dataset for species and morphological terms named entity recognition in French botanical text. FloraNER is a distantly supervised named entity recognition dataset (NER). The dataset is built from botanical French… Data in Brief vol. 56, , p. 110824 ISBN: 2352-3409 Type: 10.1016/j.dib.2024.110824
, mars 2024 — « A transformer-based nlp pipeline for enhanced extraction of botanical information using camembert on french literature » in 5th International Conference on NLP & Information Retrieval (NLPI 2024).. This research investigates the untapped wealth of centuries-old French botanical literature, particularly focused on floras,… vol. 14, n° 06, p. 59-78 Type: 10.5121/csit.2024.140605
ISBN
978-1-923107-22-9