{"slug": "candidate-generation-and-definition-guided-verification-for-sentence-level", "title": "Candidate Generation and Definition-Guided Verification for Sentence-Level Depression Symptom Recognition", "summary": "Researchers proposed a two-stage framework for sentence-level depression symptom recognition that separates symptom-candidate generation from definition-grounded verification, achieving the best accuracy and F1 scores among all baselines tested. The framework uses a contrastively fine-tuned sentence encoder to generate a symptom candidate per sentence and a fine-tuned language model to verify the candidate against a diagnostic definition. A preliminary clinical audit showed moderate alignment with diagnostic definitions, with explanation quality strongly dependent on prediction correctness, and performance remained limited for rare categories.", "body_md": "arXiv:2609.01833v1 Announce Type: new\nAbstract: Sentence-level recognition of depression symptoms is challenging because similar expressions can differ in symptom relevance, and language-model inference is insufficiently grounded in diagnostic definitions. This study proposes a two-stage framework separating symptom-candidate generation from definition-grounded verification. A contrastively fine-tuned sentence encoder generates a symptom candidate per sentence, and a fine-tuned language model verifies whether the candidate is present or absent using the sentence, its context, and a candidate-specific diagnostic definition, checking its judgment against that definition before answering. Evaluated against encoder, inference-based, medical, and general LLM baselines and a matched single-stage supervised classifier, the proposed pipeline attains the best accuracy and F1 scores of all methods, with rationales matching expert-authored annotations. A preliminary clinical audit indicates moderate alignment with diagnostic definitions, with explanation quality strongly dependent on prediction correctness. The results support decomposing symptom recognition into candidate generation and definition-grounded verification, though performance remains limited for rare categories.", "url": "https://wpnews.pro/news/candidate-generation-and-definition-guided-verification-for-sentence-level", "canonical_source": "https://arxiv.org/abs/2609.01833", "published_at": "2026-09-03 04:00:00+00:00", "updated_at": "2026-09-03 04:25:39.256311+00:00", "lang": "en", "topics": ["natural-language-processing", "artificial-intelligence", "machine-learning"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/candidate-generation-and-definition-guided-verification-for-sentence-level", "markdown": "https://wpnews.pro/news/candidate-generation-and-definition-guided-verification-for-sentence-level.md", "text": "https://wpnews.pro/news/candidate-generation-and-definition-guided-verification-for-sentence-level.txt", "jsonld": "https://wpnews.pro/news/candidate-generation-and-definition-guided-verification-for-sentence-level.jsonld"}}