All Stories

  1. Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
  2. Identifying Knowledge Editing Types in Large Language Models
  3. Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
  4. Learning Feasible Causal Algorithmic Recourse: A Prior Structural Knowledge Free Approach
  5. Don’t Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
  6. Divide-and-Conquer: Automating Code Revisions via Localization-and-Revision
  7. One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program Repair
  8. AutoRIC: Automated Neural Network Repairing Based on Constrained Optimization
  9. CAREER: Context-Aware API Recognition with Data Augmentation for API Knowledge Extraction
  10. When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
  11. Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning
  12. An Extensive Study on Adversarial Attack against Pre-trained Models of Code
  13. Natural Language to Code: How Far Are We?
  14. CCT5: A Code-Change-Oriented Pre-trained Model
  15. Two Birds with One Stone: Boosting Code Generation and Code Search via a Generative Adversarial Network
  16. Pre-Implementation Method Name Prediction for Object-Oriented Programming
  17. Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
  18. Reentrancy Vulnerability Detection and Localization: A Deep Learning Based Two-phase Approach
  19. Is this Change the Answer to that Problem?
  20. Context-Aware Code Change Embedding for Better Patch Correctness Assessment
  21. Fine-grained code-comment semantic interaction analysis
  22. Lightweight global and local contexts guided method name recommendation with prior knowledge
  23. Automated patch correctness assessment
  24. On the efficiency of test suite based program repair