Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models

Documenti analoghi

• Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions
  di: Savolainen, Oliver, et al.
  Pubblicazione: (2025)
• Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25
  di: Lu, Meng, et al.
  Pubblicazione: (2025)
• Evaluating Search System Explainability with Psychometrics and Crowdsourcing
  di: Chen, Catherine, et al.
  Pubblicazione: (2022)
• SSE: A Metric for Evaluating Search System Explainability
  di: Chen, Catherine, et al.
  Pubblicazione: (2023)
• MechIR: A Mechanistic Interpretability Framework for Information Retrieval
  di: Parry, Andrew, et al.
  Pubblicazione: (2025)