Skip to content

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

· 0 citations · 10 references

TL;DR

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.

View source

Similar papers

IReL_IIT(BHU) at HAHA 2026: A Fine-Tuning Pipeline for Satire and LLM-Generated Humor Detection in Spanish News Headlines

The participation of team IReL_IIT(BHU) in Subtasks 1 and 2 of the HAHA 2026 shared task at IberLEF 2026 is described, finding that despite class-balanced training data, the Subtask 1 model exhibited a conservative bias toward the real class, whereas the same pipeline generalized considerably better to the surface-leve...

Arjun Mukherjee, Sukomal Pal · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.