Imagen de Portada

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ni, Shiyu, Bi, Keping, Guo, Jiafeng, Cheng, Xueqi
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation
por: Tang, Minghao, et al.
Publicado: (2025)

How Knowledge Popularity Influences and Enhances LLM Knowledge Boundary Perception
por: Ni, Shiyu, et al.
Publicado: (2025)

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning
por: Cui, Wanqing, et al.
Publicado: (2024)

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation
por: Zhang, Hengran, et al.
Publicado: (2025)

A Comparative Study of Specialized LLMs as Dense Retrievers
por: Zhang, Hengran, et al.
Publicado: (2025)

LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation
por: Zhang, Hengran, et al.
Publicado: (2025)

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
por: Ding, Hanxing, et al.
Publicado: (2024)

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
por: Huang, Wei, et al.
Publicado: (2025)

Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation
por: Tang, Minghao, et al.
Publicado: (2025)

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
por: Zhang, Hengran, et al.
Publicado: (2024)

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
por: Zhang, Hengran, et al.
Publicado: (2025)

Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation
por: Zhang, Hengran, et al.
Publicado: (2025)

Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
por: Ni, Shiyu, et al.
Publicado: (2025)

LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs
por: Yang, Sihui, et al.
Publicado: (2024)

How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
por: Tu, Minzhu, et al.
Publicado: (2026)

Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?
por: Ni, Shiyu, et al.
Publicado: (2024)

Annotation-Efficient Universal Honesty Alignment
por: Ni, Shiyu, et al.
Publicado: (2025)

Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
por: Ding, Zhikai, et al.
Publicado: (2025)

Beyond Relevance: Utility-Centric Retrieval in the LLM Era
por: Zhang, Hengran, et al.
Publicado: (2026)

When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
por: Wang, Yongjie, et al.
Publicado: (2025)

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
por: Wen, Yuchen, et al.
Publicado: (2024)

Estimating Commonsense Plausibility through Semantic Shifts
por: Cui, Wanqing, et al.
Publicado: (2025)

RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
por: Guo, Yucan, et al.
Publicado: (2025)

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models
por: Xu, Yilong, et al.
Publicado: (2025)

Bridging Queries and Tables through Entities in Table Retrieval
por: Li, Da, et al.
Publicado: (2025)

Retrieval-Augmented Generation by Evidence Retroactivity in LLMs
por: Xiao, Liang, et al.
Publicado: (2025)

Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
por: Wang, Dingmin, et al.
Publicado: (2025)

Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning
por: Bi, Keping, et al.
Publicado: (2024)

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
por: Wei, Wenda, et al.
Publicado: (2025)

Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective
por: Li, Da, et al.
Publicado: (2025)

Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
por: Chen, Lu, et al.
Publicado: (2024)

LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation
por: Chen, Yen-Shan, et al.
Publicado: (2024)

Streamlining Industrial Contract Management with Retrieval-Augmented LLMs
por: Topollai, Kristi, et al.
Publicado: (2025)

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
por: Yao, Jiayu, et al.
Publicado: (2025)

Event Temporal Relation Extraction based on Retrieval-Augmented on LLMs
por: Zhang, Xiaobin, et al.
Publicado: (2024)

Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness
por: Bernardelle, Pietro, et al.
Publicado: (2026)

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
por: Xu, Shicheng, et al.
Publicado: (2024)

Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer
por: Yang, Haoyan, et al.
Publicado: (2024)

Do Retrieval Augmented Language Models Know When They Don't Know?
por: Zhou, Youchao, et al.
Publicado: (2025)

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs
por: Soligo, Anna, et al.
Publicado: (2026)