Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive …
This paper introduces v0. 5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to …
AI and NLP publication venues have increasingly encouraged researchers to reflect on possible ethical considerations, adverse impacts, and other responsible AI issues their work …
Abstract As Large Language Models and Natural Language Processing (NLP) technology rapidly develops and spreads into daily life, it becomes crucial to anticipate how its use …
The output tendencies of Pre-trained Language Models (PLM) vary markedly before and after Fine-Tuning (FT) due to the updates to the model parameters. These divergences in …
S Cui, Z Zhang, Y Chen, W Zhang, T Liu… - arXiv preprint arXiv …, 2023 - arxiv.org
The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and …
S Lin - The Journals of Gerontology: Series B, 2024 - academic.oup.com
Abstract Objectives Immigrants to Canada tend to have a lower incidence of diagnosed depression than nonimmigrants. One theory suggests that this “healthy immigrant effect …
Y Zhao, B Wang, D Zhao, K Huang, Y Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent researches indicate that Pre-trained Large Language Models (LLMs) possess cognitive constructs similar to those observed in humans, prompting researchers to …
Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to behave identically for social groups …