"au:"Rahul Seetharaman"" — arXiv2 SearchShowing 1–9 of 9 results
/ Date/ Name
Mar 22, 2026ECI: Effective Contrastive Information to Evaluate Hard-NegativesMar 5, 2026Scaling Laws for Cross-Encoder RerankingJul 7, 2025"Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language ModelsFeb 16, 2022Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI WorkloadsJun 18, 2024From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queriesJun 17, 2025InsertRank: LLMs can reason over BM25 scores to Improve Listwise RerankingAug 18, 2025Leveraging Large Language Models for Predictive Analysis of Human MiseryOct 1, 2024Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysisFeb 7, 2026From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection