Automatic evaluation of open-ended question answering in specialized domains remains challenging mainly because it relies on manual annotations from domain experts. In this work, we assess the ability of several large language models (LLMs), including closed-access (GPT-5.1, Gemini-2.5-Pro), open-source general-purpose (Qwen-80B), and biomedical domain-adapted models (MedGemma-27B, Phi-3.5-mini variants), to act as automatic evaluators of semantic equivalence in French medical open-ended QA. Our analysis reveals that LLM-based judgments are sensitive to the source of answer generation: judgement correlation varies substantially across different generator models. Among the judges, MedGemma-27B and Qwen-80B achieve the highest agreement with expert annotations in terms of F1 score and Pearson correlation. We further explore lightweight adaptation strategies on Phi-3.5-mini using supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). Even with 184 training instances, these adaptations significantly improve Phi-3.5’s results and reduce variability across answer generators, achieving performance comparable to larger domain-adapted models. Our results highlight the importance of generator-aware evaluation, the limitations of general-purpose LLMs in domain-specific settings, and the effectiveness of lightweight adaptation for compact models in low-resource scenarios.

We explore a generative relation extraction (RE) pipeline tailored to the study of interactions in the intestinal microbiome, a complex and low-resource biomedical domain. Our method leverages summarization with large language models (LLMs) to refine context before extracting relations via instruction-tuned generation. Preliminary results on a dedicated corpus show that summarization improves generative RE performance by reducing noise and guiding the model. However, BERT-based RE approaches still outperform generative models. This ongoing work demonstrates the potential of generative methods to support the study of specialized domains in low-resources setting.

Biomedical information extraction is crucial for advancing research, enhancing healthcare, and discovering treatments by efficiently analyzing extensive data. Given the extensive amount of biomedical data available, automated information extraction methods are necessary due to manual extraction’s labor-intensive, expertise-dependent, and costly nature. In this paper, we propose a novel two-stage system for information extraction where we annotate biomedical articles based on a specific ontology (HOIP). The major challenge is annotating relation between biomedical processes often not explicitly mentioned in text articles. Here, we first predict the candidate processes and then determine the relationships between these processes. The experimental results show promising outcomes in mention-agnostic process identification using Large Language Models (LLMs). In relation classification, BERT-based supervised models still outperform LLMs significantly. The end-to-end evaluation results suggest the difficulty of this task and room for improvement in both process identification and relation classification.

The biomedical domain has sparked a significant interest in the field of Natural Language Processing (NLP), which has seen substantial advancements with pre-trained language models (PLMs). However, comparing these models has proven challenging due to variations in evaluation protocols across different models. A fair solution is to aggregate diverse downstream tasks into a benchmark, allowing for the assessment of intrinsic PLMs qualities from various perspectives. Although still limited to few languages, this initiative has been undertaken in the biomedical field, notably English and Chinese. This limitation hampers the evaluation of the latest French biomedical models, as they are either assessed on a minimal number of tasks with non-standardized protocols or evaluated using general downstream tasks. To bridge this research gap and account for the unique sensitivities of French, we present the first-ever publicly available French biomedical language understanding benchmark called DrBenchmark. It encompasses 20 diversified tasks, including named-entity recognition, part-of-speech tagging, question-answering, semantic textual similarity, or classification. We evaluate 8 state-of-the-art pre-trained masked language models (MLMs) on general and biomedical-specific data, as well as English specific MLMs to assess their cross-lingual capabilities. Our experiments reveal that no single model excels across all tasks, while generalist models are sometimes still competitive.

Nous nous intéressons à l’extraction de relations, dans des articles scientifiques, portant sur le microbiome humain. Afin de construire un corpus annoté, nous avons évalué l’utilisation de l’ontologie OHMI pour détecter les relations présentes dans les phrases des articles scientifiques, en calculant la similarité sémantique entre les relations définies dans l’ontologie et les phrases des articles. Le modèle BERT et trois variantes biomédicales sont utilisés pour obtenir les représentations des relations et des phrases. Ces modèles sont comparés sur un corpus construit à partir d’articles scientifiques complets issus de la plateforme ISTEX, dont une sous-partie a été annotée manuellement.

We present a manually annotated new corpus, Species-Species Interaction (SSI), for extracting meaningful binary relations between species, in biomedical texts, at sentence level, with a focus on the gut microbiota. The corpus leverages PubTator to annotate species in full-text articles after evaluating different NER species taggers. Our first results are promising for extracting relations between species using BERT and its biomedical variants.