4 papers
FairPO: Robust Preference Optimization for Fair Multi-Label Learning
Soumen Kumar Mondal, Prateek Chanda, Akshit Varmora +1
Multi-label classification (MLC) often suffers from performance disparities across labels. We propose \textbf{FairPO}, a framework combining preference-based loss and group-robust…
Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer
Soumen Kumar Mondal, Sayambhu Sen, Abhishek Singhania +1
Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource l…
LoFTI: Localization and Factuality Transfer to Indian Locales
Sona Elza Simon, Soumen Kumar Mondal, Abhishek Singhania +2
Large language models (LLMs) encode vast amounts of world knowledge acquired via training on large web-scale datasets crawled from the internet. However, these datasets typically e…
Fuzzy Set with Hyperbolic Valued Membership Function
Chinmay Ghosh, Sanjib Kumar Datta, Soumen Mondal
In this article, we have introdued D-fuzzy sets. We have discussed the notions of inclusion, union, intersection, complementation and convexity of such D-fuzzy sets. Also we have p…