paper-with-me

Papers

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

2024-05-03 · Catherine Chen, Jack Merullo, Carsten Eickhoff

Neural models have demonstrated remarkable performance across diverse ranking tasks. However, the processes and internal mechanisms along which they determine relevance are still largely unknown. Existing approaches for analyzing neural ranker behavior with respect to IR properties rely either on assessing overall model behavior or employing probing methods that may offer an incomplete understanding of causal mechanisms. To provide a more granular understanding of internal model decision-making processes, we propose the use of causal interventions to reverse engineer neural rankers, and demonstrate how mechanistic interpretability methods can be used to isolate components satisfying term-frequency axioms within a ranking model. We identify a group of attention heads that detect duplicate tokens in earlier layers of the model, then communicate with downstream heads to compute overall document relevance. More generally, we propose that this style of mechanistic analysis opens up avenues for reverse engineering the processes neural retrieval models use to compute relevance. This work aims to initiate granular interpretability efforts that will not only benefit retrieval model development and training, but ultimately ensure safer deployment of these models.

📄 PDF Abstract BibTeX arXiv:2405.02503

Code (2)

catherineschen/axiomatic-ir-interventions 공식 구현 jax
oliversavolainen/axiomatic-ir-reproduce jax

Tasks

Decision MakingRetrieval

Similar Papers 제목 키워드 기반

Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions

2025-05-04 · Oliver Savolainen, Dur e Najaf Amjad, Roxana Petcu

This reproducibility study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models," which investigates how neural retrieval models encode t…

Information RetrievalRetrieval

Teaching Transformers Causal Reasoning through Axiomatic Training

2024-07-10 · Aniket Vashishtha, Abhinav Kumar, Atharva Pandey, Abbavaram Gowtham Reddy 외

For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since active interventions are costly, we study to what extent a system can learn causal reasoning from symbolic demonstrat…

Inductive Bias

Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models

2020-12-06 · Dong Wang, Yuewei Yang, Chenyang Tao, Zhe Gan 외

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming…

Contrastive LearningData IntegrationRepresentation Learning

Experimental Design for Causal Effect Identification

2022-05-04 · Sina Akbari, Jalal Etesami, Negar Kiyavash

Pearl's do calculus is a complete axiomatic approach to learn the identifiable causal effects from observational data. When such an effect is not identifiable, it is necessary to perform a collection of often costly inte…

Experimental Design

Mechanistic Decoding of Cognitive Constructs in Large Language Models

2026-04-16 · Yitong Shou, Manhao Guan arxiv

While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often …