Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders - Sorbonne Université
Communication Dans Un Congrès Année : 2024

Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders

Résumé

With the recent addition of Retrieval-Augmented Generation (RAG), the scope and importance of Information Retrieval (IR) has expanded. As a result, the importance of a deeper understanding of IR models also increases. However, interpretability in IR remains under-explored, especially when it comes to the models' inner mechanisms. In this paper, we explore the possibility of adapting Integrated Gradient-based methods in an IR context to identify the role of individual neurons within the model. In particular, we provide new insights into the role of what we call "relevance" neurons, as well as how they deal with unseen data. Finally, we carry out an in-depth pruning study to validate our findings.

Dates et versions

hal-04668348 , version 1 (06-08-2024)

Identifiants

Citer

Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders. ICTIR '24: The 2024 ACM SIGIR International Conference on the Theory of Information Retrieval, Jul 2024, Washington DC, United States. pp.133-143, ⟨10.1145/3664190.3672528⟩. ⟨hal-04668348⟩
33 Consultations
0 Téléchargements

Altmetric

Partager

More