Search results
Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. Toxigen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. arXiv preprint arXiv:2203.09509 (2022).
Jun 18, 2024 · It is found that even without stereotypes in reference texts, LLMs often generated culturally insensitive content during their tasks, and five state-of-the-art models are evaluated. Large Language Models (LLMs) are increasingly being used in educational and learning applications. Research has demonstrated that controlling for style, to fit the needs of the learner, fosters increased ...
Jun 20, 2024 · Additionally, proposed methods using quantity cell filtering and semantic mapping are evaluated against adversarial examples. The severe 30%+ degradation in performance and modest improvements using mitigation methods establish a strong need to both build bigger datasets as well as models that can more robustly handle adversarial inputs.
Jun 14, 2024 · This work introduces CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts, and validate the feasibility of automatic evaluation as a substitute for human evaluation and conduct comprehensive automatic safety assessments on mainstream Chinese LLMs. With the profound development of ...
Jun 10, 2024 · This paper presents an approach for word-sense disambiguation of dog whistles from standard speech using Large Language Models (LLMs), and uses this technique to create the largest dataset of disambiguated dog whistle usage, created for applications in hate speech detection, neology, and political science. A dog whistle is a form of coded communication that carries a secondary meaning to ...
Jun 13, 2024 · Semantic Scholar is a tool for researchers and postgraduate students to help you find research papers and related studies. You can create a library to organise your content and it can create a citations.
Jun 5, 2024 · Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. Toxigen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. arXiv preprint arXiv:2203.09509 (2022). Google Scholar; Joseph Henrich, Steven J Heine, and Ara Norenzayan. 2010.
