Search Results for author:
Found 9 papers, 1 papers with code
AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs
Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications.
ActiveDP: Bridging Active Learning and Data Programming
Modern machine learning models require large labelled datasets to achieve good performance, but manually labelling large datasets is expensive and time-consuming.
Can Large Language Models Design Accurate Label Functions?
This evaluation unveils both the strengths and limitations of contemporary PLMs in LF design.
Effective Explanations for Entity Resolution Models
CERTA builds on a probabilistic framework that aims at computing the explanations evaluating the outcomes produced by using perturbed copies of the input records.
Efficient Construction of Nonlinear Models over Normalized Data
For the case of NN, we propose algorithms to train the network taking normalized data as the input.
Evaluating Temporal Queries Over Video Feeds
We propose two techniques, MFS and SSG, to organize all detected objects in the intermediate data generation layer, which effectively, given the queries, minimizes the number of objects and frames that have to be considered during query evaluation.
Video Monitoring Queries
We demonstrate that the application of the techniques proposed in conjunction with declarative queries on video streams can dramatically increase the frame processing rate and speed up query processing by at least two orders of magnitude.
Multi-Attribute Selectivity Estimation Using Deep Learning
Selectivity estimation - the problem of estimating the result size of queries - is a fundamental problem in databases.
Approximate Query Processing using Deep Generative Models
We use deep generative models, an unsupervised learning based approach, to learn the data distribution faithfully such that aggregate queries could be answered approximately by generating samples from the learned model.
