Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges

Documenti analoghi

• Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation
  di: Tamber, Manveer Singh, et al.
  Pubblicazione: (2025)
• Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models
  di: Tamber, Manveer Singh, et al.
  Pubblicazione: (2024)
• Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
  di: Tamber, Manveer Singh, et al.
  Pubblicazione: (2025)
• Unifying Adversarial Robustness and Training Across Text Scoring Models
  di: Tamber, Manveer Singh, et al.
  Pubblicazione: (2026)
• Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents
  di: Sharifymoghaddam, Sahel, et al.
  Pubblicazione: (2026)