no code implementations • 10 Feb 2024 • Rudrajit Das, Xi Chen, Bertram Ieong, Parikshit Bansal, Sujay Sanghavi
In this work, we focus on the greedy approach of selecting samples with large \textit{approximate losses} instead of exact losses in order to reduce the selection overhead.
no code implementations • 27 Jun 2023 • Parikshit Bansal, Amit Sharma
Instead, we propose a sampling strategy based on the difference in prediction scores between the base model and the finetuned NLP model, utilizing the fact that most NLP models are finetuned from a base model.
no code implementations • 26 May 2023 • Parikshit Bansal, Amit Sharma
Therefore, using methods from the causal inference literature, we propose an algorithm to regularize the learnt effect of the features on the model's prediction to the estimated effect of feature on label.
no code implementations • 7 Oct 2022 • Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma
To explain this generalization failure, we consider an intervention-based importance metric, which shows that a fine-tuned model captures spurious correlations and fails to learn the causal features that determine the relevance between any two text inputs.
1 code implementation • 2 Mar 2021 • Parikshit Bansal, Prathamesh Deshpande, Sunita Sarawagi
Missing values are commonplace in decision support platforms that aggregate data over long time stretches from disparate sources, and reliable data analytics calls for careful handling of missing data.