no code implementations • 22 Feb 2024 • Spencer Rarrick, Ranjita Naik, Sundar Poudel, Vishal Chowdhary
Neural Machine Translation (NMT) continues to improve in quality and adoption, yet the inadvertent perpetuation of gender bias remains a significant concern.
no code implementations • 27 Nov 2023 • Ranjita Naik, Spencer Rarrick, Vishal Chowdhary
By using this data to fine-tune an existing NMT model, they show that gender bias can be significantly mitigated, albeit at the expense of translation quality due to catastrophic forgetting.
no code implementations • 15 Nov 2023 • Spencer Rarrick, Ranjita Naik, Sundar Poudel, Vishal Chowdhary
To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English.
1 code implementation • 24 Oct 2023 • Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yuksekgonul, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi
Motivated by rising concerns around factual incorrectness and hallucinations of LLMs, we present KITAB, a new dataset for measuring constraint satisfaction abilities of language models.
no code implementations • 11 Oct 2023 • Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul, Hamid Palangi, Besmira Nushi
Large language models (LLMs) are documented to struggle in settings that require complex reasoning.
1 code implementation • 26 Sep 2023 • Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text.
no code implementations • 30 Mar 2023 • Ranjita Naik, Besmira Nushi
In this paper, we take a multi-dimensional approach to studying and quantifying common social biases as reflected in the generated images, by focusing on how occupations, personality traits, and everyday situations are depicted across representations of (perceived) gender, age, race, and geographical location.
1 code implementation • 7 Mar 2023 • Spencer Rarrick, Ranjita Naik, Varun Mathur, Sundar Poudel, Vishal Chowdhary
Although recent years have brought significant progress in improving translation of unambiguously gendered sentences, translation of ambiguously gendered input remains relatively unexplored.