一作ACL 2026Findings· Findings of ACL
Can LLM s Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility
Nickil Maveli · Antonio Vergari · Shay B Cohen
摘要
LLMs demonstrate strong performance on code benchmarks, yet round-trip code execution reveals limitations in their ability to maintain consistent reasoning across forward and backward execution. We present RoundTripCodeEval (RTCE), a comprehensive benchmark consisting of four distinct code execut...