2 citations · 2 across the 2 of their papers we have counts for
7 papers
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs
Anjishnu Mukherjee, Chutong Meng, Antonios Anastasopoulos
This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appear multilingual largely beca…
Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
Jinhao Pan, Chahat Raj, Anjishnu Mukherjee +4
Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm…
MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering
Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos
Large language models can memorize competing locale-specific facts yet fail to select among them when the locale changes, defaulting instead to a single globally dominant answer. W…
Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations
Mamnuya Rinki, Chahat Raj, Anjishnu Mukherjee +1
Evaluations of Large Language Models (LLMs) often overlook intersectional and culturally specific biases, particularly in underrepresented multilingual regions like South Asia. Thi…
Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis
Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan +2
Large Language Models (LLMs) perpetuate social biases, reflecting prejudices in their training data and reinforcing societal stereotypes and inequalities. Our work explores the pot…
Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models
Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos
We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated…