Unifying Corroborative and Contributive Attributions in Large Language Models

no code implementations • 20 Nov 2023 • Theodora Worledge, Judy Hanwen Shen, Nicole Meister, Caleb Winston, Carlos Guestrin

As businesses, products, and services spring up around large language models, the trustworthiness of these models hinges on the verifiability of their outputs.

Language Modelling Large Language Model +1

A Retrospective on ICSE 2022

no code implementations • 26 Jul 2022 • Cailin Winston, Caleb Winston, Chloe Winston, Claris Winston, Cleah Winston

The 44th International Conference on Software Engineering (ICSE 2022) was held in person from May 22 to May 27, 2022 in Pittsburgh, PA, USA.

Repairing Brain-Computer Interfaces with Fault-Based Data Acquisition

no code implementations • 20 Mar 2022 • Cailin Winston, Caleb Winston, Chloe N Winston, Claris Winston, Cleah Winston, Rajesh Pn Rao, René Just

Specifically, it proposes partial test oracles as a method for detecting faults and slice functions as a method for localizing faults to characteristic patterns in the input data or relevant tasks performed by the user.