Roman_lab at MIRROR@IberLEF 2026: Style-Aware Synthetic Data Generation for Motivational Interviewing

Prompt-Driven Synthetic Data Generation for MITI Behavior Code Classification: A Diversity-Aware Few-Shot Approach

Metric-Aware Calibration and Generate–Critic Reranking for Spanish Humor Analysis and Generation

The results indicate that short Spanish humor classification benefits from separating probability estimation from operating-point calibration, while generate–critic reranking provides a practical strategy for preference-oriented humor generation.

SINAI at HISEMOTIONS in IberLEF 2026: Three-Phase Fine-Tuning of a Domain-Adaptive BERT for Historical Emotion Detection

MNN at HAHA@IberLEF 2026 Task-Adaptive Reasoning and Fine-Tuning for Spanish Humor Detection

Results show that the two subtasks behave differently in practice: satirical headline detection is better handled by prompting a large instruction-following model, while LLM-generated joke detection benefits more from supervised learning over dataset-specific stylistic and length-related cues.

UCO-UC-CICESE-Plenitas Team at HAHA: Humor Analysis based on Human Annotation and Automatic Humor Generation using Embeddings and Large Language Models

UCO-UC-CICESE-Plenitas Team at Exploring the Historical Text-Based Emotion Detection in Early Modern Spanish Correspondence Using Large Language Model and Embeddings