Saved in:
Bibliographic Details
Main Authors: Cai, Zhixin, Bai, Jun, Liu, Yang, Li, Jiaqi, Zhang, Yichi, Li, Taichuan, Chen, Zhuofan, Jia, Zixia, Zheng, Zilong, Rong, Wenge
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913169837916160
author Cai, Zhixin
Bai, Jun
Liu, Yang
Li, Jiaqi
Zhang, Yichi
Li, Taichuan
Chen, Zhuofan
Jia, Zixia
Zheng, Zilong
Rong, Wenge
author_facet Cai, Zhixin
Bai, Jun
Liu, Yang
Li, Jiaqi
Zhang, Yichi
Li, Taichuan
Chen, Zhuofan
Jia, Zixia
Zheng, Zilong
Rong, Wenge
contents Explaining why dense retrievers assign high relevance scores remains challenging because retrieval decisions are made through opaque high-dimensional embeddings. Existing explanations often focus on surface signals, such as lexical matches, token alignments, or post-hoc textual rationales, and thus provide limited insight into the latent factors that shape dense retrieval behavior at the embedding level. We propose \textit{Xetrieval}, an embedding-level mechanistic framework for explaining dense retrieval. \textit{Xetrieval} first introduces a lightweight reasoning internalizer that approximates Chain-of-Thought reasoning directly in the embedding space with a single forward pass, enriching sentence embeddings with reasoning-oriented information while avoiding expensive autoregressive generation. It then decomposes these reasoning-enhanced embeddings into sparse, human-interpretable features, each associated with a coherent natural language description. By aggregating sparse feature overlaps across multiple document-side views, \textit{Xetrieval} provides feature-level explanations of individual retrieval decisions. Experiments on diverse retrievers and benchmarks show that \textit{Xetrieval} uncovers coherent interpretable features, yields stronger pair-level intervention effects, and supports task-level feature steering. The project page and source code are available at https://hihiczx.github.io/Xetrieval .
format Preprint
id arxiv_https___arxiv_org_abs_2605_29507
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Xetrieval: Mechanistically Explaining Dense Retrieval
Cai, Zhixin
Bai, Jun
Liu, Yang
Li, Jiaqi
Zhang, Yichi
Li, Taichuan
Chen, Zhuofan
Jia, Zixia
Zheng, Zilong
Rong, Wenge
Artificial Intelligence
Information Retrieval
Explaining why dense retrievers assign high relevance scores remains challenging because retrieval decisions are made through opaque high-dimensional embeddings. Existing explanations often focus on surface signals, such as lexical matches, token alignments, or post-hoc textual rationales, and thus provide limited insight into the latent factors that shape dense retrieval behavior at the embedding level. We propose \textit{Xetrieval}, an embedding-level mechanistic framework for explaining dense retrieval. \textit{Xetrieval} first introduces a lightweight reasoning internalizer that approximates Chain-of-Thought reasoning directly in the embedding space with a single forward pass, enriching sentence embeddings with reasoning-oriented information while avoiding expensive autoregressive generation. It then decomposes these reasoning-enhanced embeddings into sparse, human-interpretable features, each associated with a coherent natural language description. By aggregating sparse feature overlaps across multiple document-side views, \textit{Xetrieval} provides feature-level explanations of individual retrieval decisions. Experiments on diverse retrievers and benchmarks show that \textit{Xetrieval} uncovers coherent interpretable features, yields stronger pair-level intervention effects, and supports task-level feature steering. The project page and source code are available at https://hihiczx.github.io/Xetrieval .
title Xetrieval: Mechanistically Explaining Dense Retrieval
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2605.29507