4 papers
Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation
Nishit Singh
Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outp…
Causal Evidence of Stack Representations in Modeling Counter Languages Using Transformers
Nishit Singh
Formal languages have proven to be effective conduits to understand the inner mechanisms of transformers. Past work has shown that transformers trained on next token prediction ove…
Emergent Ordinal Geometry in Transformers Trained on Local Comparisons
Nishit Singh
Transitive inference is the challenge of inferring that A < C from knowing only adjacent relations (A < B, B < C). It is solved by humans and animals not through logical chaining b…
MMCFND: Multimodal Multilingual Caption-aware Fake News Detection for Low-resource Indic Languages
Shubhi Bansal, Nishit Sushil Singh, Shahid Shafi Dar +1
The widespread dissemination of false information through manipulative tactics that combine deceptive text and images threatens the integrity of reliable sources of information. Wh…