Hongyin Luo

Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning

2023 · arXiv (Cornell University)

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of stereotypes concerning different …

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

2023 · arXiv (Cornell University)

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs that …