10 papers
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the secur…
Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models
Manuel Mondal, Ljiljana Dolamic, Gérôme Bovet +2
The handling of probabilities in the form of uncertainty or partial information is an essential task for LLMs in many settings and applications. A common approach to evaluate an LL…
From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting
Cyril Vallez, Alexander Sternfeld, Andrei Kucharavy +1
As the role of Large Language Models (LLM)-based coding assistants in software development becomes more critical, so does the role of the bugs they generate in the overall cybersec…
Are the LLMs Capable of Maintaining at Least the Language Genus?
Sandra MitroviÄ, David Kletz, Ljiljana Dolamic +1
Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In…
TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critic…
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks
Vani Kanjirangat, Tanja SamardžiÄ, Ljiljana Dolamic +1
Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related t…