Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models - Lecture 3

Explore a 14-minute conference talk from SIGIR 2024 that delves into axiomatic causal interventions for reverse engineering relevance computation in neural retrieval models. Learn from authors Catherine Chen, Jack Merullo, and Carsten Eickhoff as they present their research on neural information retrieval. Gain insights into innovative techniques for understanding and improving the relevance computation process in advanced retrieval systems.

SIGIR 2024 T2.3 [pp] Axiomatic Causal Interventions for Reverse Engineering Relevance Computation