semeval

This paper presents UCSC NLP's systems for SemEval-2026 Task 10 (PsyCoMark), addressing conspiracy marker extraction using boundary-aware span extraction with RoBERTa, and document-level conspiracy classification with label smoothing. The systems ranked 7th in subtask 1 and 12th in subtask 2.

This paper presents the Invariant-Variant Disentangled State-Space Model (IVD-SSM), a submission to SemEval-2026 Task 4, which uses a hybrid Jamba-1.5-Mini backbone and a novel Structurally Gated Alignment head to disentangle structural invariants from lexical variants for narrative similarity assessment.

This paper presents methods for SemEval-2026 Task 3, using transformer ensembles and LLM-generated annotations to predict continuous valence and arousal scores in dimensional aspect-based sentiment analysis.

This paper describes a system for SemEval-2026 Task 9 on multilingual polarization detection, using RoBERTa for English and AfroXLMR for Swahili with class-weighted loss and threshold tuning, achieving competitive F1 scores on binary and multi-label subtasks.

This paper presents SALSA, a single-pass autoregressive LLM structured classification method for detecting machine-generated code, achieving strong OOD generalization at SemEval-2026 Task 13.

This paper presents a system for constrained humor generation that uses a generate-many select-best strategy with a preference model learned from human comparisons. It achieved top ranks in English and Chinese subtasks and second in Spanish at SemEval-2026 Task 1.

This paper presents the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, which applies activation steering to multilingual LLMs using language vectors from parallel FLORES data. The system achieved 86.96% accuracy in the MCQ track, ranking 7th out of 17 teams, and post-hoc analyses reveal that gains are layer-sensitive and vary across language-region pairs.

This paper describes a system for SemEval-2026 Task 8 that uses a three-stage pipeline involving query rewriting with a fine-tuned Qwen model, hybrid retrieval, and cross-encoder reranking to improve multi-turn retrieval performance.

This paper details the YEZE system for SemEval-2026 Task 9, which detects online polarization in 22 languages using a heterogeneous ensemble of XLM-RoBERTa and mDeBERTa models.

This paper presents the winning system for SemEval-2026 Task 8's generation subtask, using a heterogeneous ensemble of seven LLMs with dual prompting strategies and a GPT-4o-mini judge to select the best response. The system achieved first place with a conditioned harmonic mean of 0.7827, outperforming all baselines and demonstrating the value of model diversity.