1 code implementation • 18 Mar 2024 • Huy Nghiem, Hal Daumé III
We show that pre-training models for the detection of offensive content on HateCOT significantly boots open-sourced Language Models on three benchmark datasets in both zero and few-shot settings, despite differences in domain and task.}
1 code implementation • 17 Feb 2024 • Zongxia Li, Ishani Mondal, Yijun Liang, Huy Nghiem, Jordan Lee Boyd-Graber
Question answering (QA) can only make progress if we know if an answer is correct, but for many of the most challenging and interesting QA examples, current answer correctness (AC) metrics do not align with human judgments, particularly verbose, free form answers from large language models (LLM).
1 code implementation • 5 Feb 2024 • Huy Nghiem, Umang Gupta, Fred Morstatter
The propagation of offensive content through social media channels has garnered attention of the research community.
no code implementations • 24 Jan 2024 • Zongxia Li, Ishani Mondal, Yijun Liang, Huy Nghiem, Jordan Boyd-Graber
Question answering (QA) can only make progress if we know if an answer is correct, but for many of the most challenging and interesting QA examples, current evaluation metrics to determine answer equivalence (AE) often do not align with human judgments, particularly more verbose, free-form answers from large language models (LLM).
no code implementations • 4 Dec 2021 • Huy Nghiem, Fred Morstatter
We demonstrate that we are able to identify hate speech that is systematically missed by established hate speech detectors.