2 papers
cs.CL2025
Transfer Learning via Lexical Relatedness: A Sarcasm and Hate Speech Case Study
Angelly Cabrera, Linus Lei, Antonio Ortega
Detecting hate speech in non-direct forms, such as irony, sarcasm, and innuendos, remains a persistent challenge for social networks. Although sarcasm and hate speech are regarded…
cs.HC2025
Crowd-SFT: Crowdsourcing for LLM Alignment
Alex Sotiropoulos, Sulyab Thottungal Valapu, Linus Lei +2
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences…