Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
Partha Pratim Saha, Samarth Raina, Mayur Parvatikar +4
Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally. Aligned systems still fa…
cs.CL2025
Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
Shaina Raza, Maximus Powers, Partha Pratim Saha +2
Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evalua…