5 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…
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…
Using Causal Inference to Explore Government Policy Impact on Computer Usage
Mingjia Zhu, Lechuan Wang, Julien Sebot +3
We explore the causal relationship between COVID-19 lockdown policies and changes in personal computer usage. In particular, we examine how lockdown policies affected average daily…