UCSC NLP researchers have developed systems for SemEval-2026 Task 10, focusing on conspiracy marker extraction and document-level conspiracy detection. Their approach for marker extraction involves multi-label span classification with advanced techniques like hard-negative sampling and boundary-aware representations. For document classification, they employed a sequence classifier with label smoothing. The systems achieved 7th place in marker extraction and 11th place in document detection on the official test set. AI
IMPACT This research contributes to the advancement of NLP techniques for detecting conspiracy markers and classifying conspiracy-related documents.
RANK_REASON The cluster describes a research paper detailing systems developed for a specific NLP task at a competition.
- action film
- actor
- arXiv
- evidence
- Holocaust victim
- Hugging Face
- PsyCoMark
- result
- Roberta
- SemEval-2026 Task 10
- UCSC NLP
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
