4 papers
Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
Mohamed Bouadi, Nassim Bouarour, Varun Kulkarni +3
What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost entirely from synthetic pretra…
AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Snehasis Mukhopadhyay, Aryan Kasat, Shivam Dubey +5
Large Language Models (LLMs) can inadvertently reflect societal biases present in their training data, leading to harmful or prejudiced outputs. In the Indian context, our empirica…
HumorPlanSearch: Structured Planning and HuCoT for Contextual AI Humor
Shivam Dubey
Automated humor generation with Large Language Models (LLMs) often yields jokes that feel generic, repetitive, or tone-deaf because humor is deeply situated and hinges on the liste…
Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
Shivam Dubey
As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditi…