Cover Image

How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qi, Mao, Jiaxin, Wen, Ji-Rong
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Make Large Language Model a Better Ranker
by: Chao, Wen-Shuo, et al.
Published: (2024)

Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search
by: Sachdev, Jayant, et al.
Published: (2025)

LORE: A Large Generative Model for Search Relevance
by: Lu, Chenji, et al.
Published: (2025)

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
by: Liu, Qi, et al.
Published: (2024)

An Integrated Data Processing Framework for Pretraining Foundation Models
by: Sun, Yiding, et al.
Published: (2024)

Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
by: Guo, Lingbing, et al.
Published: (2023)

DiffuRank: Effective Document Reranking with Diffusion Language Models
by: Liu, Qi, et al.
Published: (2026)

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search
by: Wu, Kaixin, et al.
Published: (2024)

Supply Chain Network Extraction and Entity Classification Leveraging Large Language Models
by: Liu, Tong, et al.
Published: (2024)

Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval
by: Ji, Luo, et al.
Published: (2024)

Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
by: Zhu, Yunchang, et al.
Published: (2023)

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
by: Qin, Zhen, et al.
Published: (2023)

LawLLM: Law Large Language Model for the US Legal System
by: Shu, Dong, et al.
Published: (2024)

Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models
by: Zhang, Jiaxin, et al.
Published: (2024)

ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
by: Zhang, Lingxi, et al.
Published: (2024)

SLMRec: Distilling Large Language Models into Small for Sequential Recommendation
by: Xu, Wujiang, et al.
Published: (2024)

Integrating Large Language Models with Graphical Session-Based Recommendation
by: Guo, Naicheng, et al.
Published: (2024)

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
by: Jin, Bowen, et al.
Published: (2024)

LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
by: Liu, Qi, et al.
Published: (2025)

Evaluating Cost-Accuracy Trade-offs in Multimodal Search Relevance Judgements
by: Terragni, Silvia, et al.
Published: (2024)

LemmaHead: RAG Assisted Proof Generation Using Large Language Models
by: Yang, Tianbo, et al.
Published: (2025)

Utilizing Large Language Models for Information Extraction from Real Estate Transactions
by: Zhao, Yu, et al.
Published: (2024)

NANOGPT: A Query-Driven Large Language Model Retrieval-Augmented Generation System for Nanotechnology Research
by: Chandrasekhar, Achuth, et al.
Published: (2025)

OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching
by: Qiang, Zhangcheng, et al.
Published: (2025)

Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning
by: Zhuang, Jun, et al.
Published: (2024)

Question-Answer Extraction from Scientific Articles Using Knowledge Graphs and Large Language Models
by: Azarbonyad, Hosein, et al.
Published: (2025)

Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models
by: Miao, Brenda Y., et al.
Published: (2024)

Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
by: Esfandiarpoor, Reza, et al.
Published: (2025)

Fine-Tuning Large Language Models and Evaluating Retrieval Methods for Improved Question Answering on Building Codes
by: Aqib, Mohammad, et al.
Published: (2025)

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA datasets with Large Language Models
by: Pradeep, Ronak, et al.
Published: (2024)

Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
by: Li, Mufei, et al.
Published: (2024)

LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation
by: Zhao, Hongke, et al.
Published: (2024)

Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking
by: LeVine, Will, et al.
Published: (2025)

Graph-based Confidence Calibration for Large Language Models
by: Li, Yukun, et al.
Published: (2024)

Large Language Models for Information Retrieval: A Survey
by: Zhu, Yutao, et al.
Published: (2023)

Editing Conceptual Knowledge for Large Language Models
by: Wang, Xiaohan, et al.
Published: (2024)

Can Small Language Models be Good Reasoners for Sequential Recommendation?
by: Wang, Yuling, et al.
Published: (2024)

Language Models As Semantic Indexers
by: Jin, Bowen, et al.
Published: (2023)

Query Performance Prediction using Relevance Judgments Generated by Large Language Models
by: Meng, Chuan, et al.
Published: (2024)

Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study
by: Niu, Zechun, et al.
Published: (2024)