Podobne knjige/članki

• Disproving Program Equivalence with LLMs
  od: Allamanis, Miltiadis, et al.
  Izdano: (2025)
• NExT: Teaching Large Language Models to Reason about Code Execution
  od: Ni, Ansong, et al.
  Izdano: (2024)
• Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
  od: Hooda, Ashish, et al.
  Izdano: (2024)
• Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation
  od: Ruiz, Fernando Vallecillos, et al.
  Izdano: (2024)
• Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
  od: Tahimic, Kriz, et al.
  Izdano: (2025)