collaborators

12 papers

cs.CL2025

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…

cs.CL2025

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…

cs.IR2025

Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures

Rahul Raja, Arpita Vats

Question Answering (QA) systems have traditionally relied on structured text data, but the rapid growth of multimedia content (images, audio, video, and structured metadata) has in…

cs.AI2025

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…

cs.LG2025

Counterfactual Risk Minimization with IPS-Weighted BPR and Self-Normalized Evaluation in Recommender Systems

Rahul Raja, Arpita Vats

Learning and evaluating recommender systems from logged implicit feedback is challenging due to exposure bias. While inverse propensity scoring (IPS) corrects this bias, it often s…

cs.LG2025

Beyond Nearest Neighbors: Semantic Compression and Graph-Augmented Retrieval for Enhanced Vector Search

Rahul Raja, Arpita Vats

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach oft…