3 papers
cs.CL2026
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
Pruthvinath Jeripity Venkata
When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved this choice depends on how well-k…
cs.CL2026
Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation
Pruthvinath Jeripity Venkata
The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studie…
cs.CL2026
When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models
Pruthvinath Jeripity Venkata
When you ask an AI assistant for advice about your career, your marriage, or a conflict with your family, does it give you the same answer regardless of where you are from? We test…