Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?

Documenti analoghi

• Leveraging Discourse Structure for Extractive Meeting Summarization
  di: Rennard, Virgile, et al.
  Pubblicazione: (2024)
• CARTE: A Benchmark for Mapping Language Model Knowledge Across France
  di: Carneiro, Sarah Almeida, et al.
  Pubblicazione: (2026)
• LLM as a Broken Telephone: Iterative Generation Distorts Information
  di: Mohamed, Amr, et al.
  Pubblicazione: (2025)
• Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning
  di: Zhang, Yang, et al.
  Pubblicazione: (2025)
• Effective faking of verbal deception detection with target-aligned adversarial attacks
  di: Kleinberg, Bennett, et al.
  Pubblicazione: (2025)