Showing cs.SEShow all
3 papers · 1 filter
cs.SE2025
Multicalibration for LLM-based Code Generation
Viola Campos, Robin Kuschnereit, Adrian Ulges
As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likeliho…
cs.SE2025
Exploring Generalizable Automated Program Repair with Large Language Models
Viola Campos, Ridwan Shariffdeen, Adrian Ulges +1
Automated Program Repair (APR) proposes bug fixes to aid developers in maintaining software. The state of the art in this domain focuses on LLMs, leveraging their strong capabiliti…
cs.SE2022
Addressing Leakage in Self-Supervised Contextualized Code Retrieval
Johannes Villmow, Viola Campos, Adrian Ulges +1
We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contr…