Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment

Documenti analoghi

• Efficient LLM Comparative Assessment: a Product of Experts Framework for Pairwise Comparisons
  di: Liusie, Adian, et al.
  Pubblicazione: (2024)
• Finetuning LLMs for Comparative Assessment Tasks
  di: Raina, Vatsal, et al.
  Pubblicazione: (2024)
• LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
  di: Liusie, Adian, et al.
  Pubblicazione: (2023)
• Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models
  di: Raina, Vyas, et al.
  Pubblicazione: (2024)
• WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
  di: Molenda, Piotr, et al.
  Pubblicazione: (2024)