All Stories

  1. How ChatGPT safety guardrails can fail under red teaming
  2. LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead
  3. Less is More: DocString Compression in Code Generation
  4. Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
  5. A First Look at On-device Models in iOS Apps
  6. Training-free Lexical Backdoor Attacks on Language Models