nicolay-r/flan-t5-emotion-cause-thor-base
Text Generation • 0.2B • Updated • 12 • 1
Nicolay Rusnachenko
nicolay-r
AI & ML interests
NLP for Healthcare ⚕️ @BU_Research・PhD in NLP / IR ・Textual Information Retrieval
Recent Activity
authored a paper about 16 hours ago
NCL-BU at SemEval-2026 Task 3: Fine-tuning XLM-RoBERTa for Multilingual Dimensional Sentiment Regression updated a collection 2 days ago
sentiment-analysis-advances posted an update 20 days ago
📢 For those who experimening with large language models in clinical domain, this might be relevant. So far we participated in Task 4 of the ArchEHR-QA 2026 shared task. The task requires aligning answers to patient questions with clinical evidence. Our approach encodes clinical reasoning principles directly into the prompt, evaluated in a zero-shot setting.
Results: +2% improvement with ChatGPT-5.2. No measurable gain with Llama-3 70B, indicating the approach benefits larger-scale models.
🌟 Code: https://github.com/nicolay-r/ArchEHR-QA-2026-Task-4-MedEvi-NS
📊 Shared task: https://www.codabench.org/competitions/13528/Organizations
None yet
nicolay-r/flan-t5-tsa-prompt-xl
Text Generation • 3B • Updated • 10 • 1
nicolay-r/flan-t5-tsa-thor-xl
Text Generation • 3B • Updated • 5 • 3
nicolay-r/flan-t5-tsa-thor-large
Text Generation • 0.8B • Updated • 3
nicolay-r/flan-t5-tsa-thor-base
Text Generation • 0.2B • Updated • 93 • 1
nicolay-r/qwen25-05b-multiclinsum-standard
Text Generation • 0.5B • Updated • 5
nicolay-r/qwen25-05b-multiclinsum-distil
Text Generation • 0.5B • Updated • 31 • 1