REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names

Read full text
Authors: Jun Yeon Won
Cited by: 1

Abstract

These are scripts and binaries of the work, ''REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names" in the AIWare 2026 conference. We are updating the project on the following Github. https://github.com/OSUSecLab/REBench

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
29 April 2026
Document type
Dataset