We have 3 of 29 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large language models (LLMs) have shown strong performance in static code tasks like code search, summarization, and generation, but remain limited in dynamic code reasoning, which involves inferring how programs behave during execution without actually running them. This limitation stems from LLMs being trained on sta...
This work proposes CodeSteer, a novel attention steering approach that reallocates model attention toward semantically relevant program elements, including backward slices for output prediction and control-flow paths for execution reasoning in large language models.
It is demonstrated that semantic self-consistency is a reliable and extensible measure to be used as a behavioral proxy for quantifying model code understandability, with broad implications in both software engineering research and practice.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
