From Brittle LLM Code Reasoning to MaxSAT-Based Verified Repairs @ UCL
In this talk, we examine the limitations of Large Language Models (LLMs) in semantic code reasoning, showing that their predictions may change under semantics-preserving code …
Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations? @ Oxford
In this talk, I will present our evaluation on whether state-of-the-art LLMs with up to 8B parameters can reason about Python programs or are simply guessing.