# UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection

arXiv: https://arxiv.org/abs/2607.05689 · HTML: https://mlsanity.com/paper/2607.05689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 3 of 3)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse](https://mlsanity.com/paper/2407.10745/) (2024)

## Abstract (arXiv)

We present our systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction (Subtask 1) and document-level conspiracy detection (Subtask 2). For marker extraction, we formulate the task as multi-label span classification over enumerated candidate spans, using IoU >= 0.95 positive labeling, hard-negative sampling, and containment-based non-maximum suppression (NMS) with boundary-aware span representations. Document classification is modeled independently using a sequence classifier with label smoothing and a stratified train-validation split. Analysis shows that entity-like roles (Actor, Victim) are detected robustly, while abstract roles (Action, Effect, Evidence) remain sensitive to boundary criteria. On the official test set, our systems rank 7th in Subtask 1 (0.2251 macro F1) and 11th in Subtask 2 (0.7694 weighted F1).