4 papers
Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis
Harshwardhan Fartale, Ashish Kattamuri, Rahul Raja +3
Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct in…
Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO
Ashish Kattamuri, Ishita Prasad, Meetu Malhotra +3
Current Text-to-SQL methods are evaluated and only focused on executable queries, overlooking the semantic alignment challenge -- both in terms of the semantic meaning of the query…
Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data
Ashish Kattamuri, Arpita Vats, Harshwardhan Fartale +3
Recursive prompting with large language models enables scalable synthetic dataset generation but introduces the risk of bias amplification. We investigate gender bias dynamics acro…
RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
Ashish Kattamuri, Harshwardhan Fartale, Arpita Vats +2
Data contamination poses a significant challenge to reliable LLM evaluation, where models may achieve high performance by memorizing training data rather than demonstrating genuine…