5 papers
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
Andrea Gurioli, Davide D'Ascenzo, Federico Pennino +2
Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authors…
Do not copy and paste! Rewriting strategies for code retrieval
Andrea Gurioli, Federico Pennino, Maurizio Gabbrielli
Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and corpora into a normalized styl…
From Reasoning to Code: GRPO Optimization for Underrepresented Languages
Federico Pennino, Bianca Raimondi, Massimo Rondelli +2
Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming languages, such as Prolog and Lisp, due…
MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings
Andrea Gurioli, Federico Pennino, João Monteiro +1
Deploying language models often requires navigating accuracy vs. performance trade-offs to meet latency constraints while preserving utility. Traditional model distillation reduces…
Is This You, LLM? Recognizing AI-written Programs with Multilingual Code Stylometry
Andrea Gurioli, Maurizio Gabbrielli, Stefano Zacchiroli
With the increasing popularity of LLM-based code completers, like GitHub Copilot, the interest in automatically detecting AI-generated code is also increasing-in particular in cont…