7 papers
Residual Skill Optimization for Text-to-SQL Ensembles
Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant +8
Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability t…
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
Parjanya Prajakta Prashant, Jiongli Zhu, Aldan Creo +1
Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existin…
Scalable Out-of-distribution Robustness in the Presence of Unobserved Confounders
Parjanya Prashant, Seyedeh Baharan Khatami, Bruno Ribeiro +1
We consider the task of out-of-distribution (OOD) generalization, where the distribution shift is due to an unobserved confounder () affecting both the covariates () and the…
KAIROS: Scalable Model-Agnostic Data Valuation
Jiongli Zhu, Parjanya Prajakta Prashant, Alex Cloninger +1
Training data increasingly shapes not only model accuracy but also regulatory compliance and market valuation of AI assets. Yet existing valuation methods remain inadequate: model-…
A Lightweight Method to Disrupt Memorized Sequences in LLM
Parjanya Prajakta Prashant, Kaustubh Ponkshe, Babak Salimi
As language models scale, their performance improves dramatically across a wide range of tasks, but so does their tendency to memorize and regurgitate parts of their training data…
Causal-Copilot: An Autonomous Causal Analysis Agent
Xinyue Wang, Kun Zhou, Wenyi Wu +10
Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algo…