4 papers · 1 filter
MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection
Ivo Bueno, Lea Hirlimann, Enkelejda Kasneci
Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While recent vision-language models (…
Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detection
Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein +1
Annotating data remains a costly bottleneck for supervised NLP. Active learning (AL) reduces the number of human labels needed by selecting only the most informative instances, whi…
SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
Leonor Veloso, Lea Hirlimann, Lucija Mihić Zidar +3
Queer vernacular is rarely studied in NLP, despite advancements in resources and evaluation for other sociolects and informal language. Because of this, NLP systems often process q…
On Relation-Specific Neurons in Large Language Models
Yihong Liu, Runsheng Chen, Lea Hirlimann +6
In large language models (LLMs), certain \emph{neurons} can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combinatio…