Imagen de Portada

Can Small Language Models Use What They Retrieve? An Empirical Study of Retrieval Utilization Across Model Scale

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Pandey, Sanchit
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quecto-V1: Empirical Analysis of 8-bit Quantized Small Language Models for On-Device Legal Retrieval
por: Dikshit, Subrit
Publicado: (2026)

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs
por: Tan, Jiejun, et al.
Publicado: (2024)

Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models
por: Buhnila, Ioana, et al.
Publicado: (2024)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
por: Ahuja, Sanchit, et al.
Publicado: (2026)

Retrieving Counterfactuals Improves Visual In-Context Learning
por: Xiong, Guangzhi, et al.
Publicado: (2026)

MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks
por: Ahuja, Sanchit, et al.
Publicado: (2023)

Dense X Retrieval: What Retrieval Granularity Should We Use?
por: Chen, Tong, et al.
Publicado: (2023)

An Empirical Study of Retrieval Augmented Generation with Chain-of-Thought
por: Zhao, Yuetong, et al.
Publicado: (2024)

Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment
por: Luo, Kun, et al.
Publicado: (2024)

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
por: Xiong, Guangzhi, et al.
Publicado: (2025)

MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars
por: Wang, Shuoyuan, et al.
Publicado: (2026)

A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation
por: Yuan, Xujie, et al.
Publicado: (2025)

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
por: Labruna, Tiziano, et al.
Publicado: (2024)

Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios
por: Du, Y., et al.
Publicado: (2025)

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
por: Weller, Orion, et al.
Publicado: (2024)

An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models
por: Feng, Yuming, et al.
Publicado: (2026)

To Case or Not to Case: An Empirical Study in Learned Sparse Retrieval
por: Lionis, Emmanouil Georgios, et al.
Publicado: (2026)

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS
por: Dou, Alex ZH, et al.
Publicado: (2025)

Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
por: Zhang, Kaiyan, et al.
Publicado: (2024)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
por: Cheng, Pengzhou, et al.
Publicado: (2024)

Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
por: Zhao, Jinman, et al.
Publicado: (2024)

Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models
por: Park, Seong-Il, et al.
Publicado: (2024)

Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models
por: Maekawa, Seiji, et al.
Publicado: (2024)

R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models
por: Zhang, Taolin, et al.
Publicado: (2024)

On Retrieval Augmentation and the Limitations of Language Model Training
por: Chiang, Ting-Rui, et al.
Publicado: (2023)

MINERS: Multilingual Language Models as Semantic Retrievers
por: Winata, Genta Indra, et al.
Publicado: (2024)

The Compressor-Retriever Architecture for Language Model OS
por: Yang, Yuan, et al.
Publicado: (2024)

Scaling Laws for Multilingual Language Models
por: He, Yifei, et al.
Publicado: (2024)

A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models
por: Zhang, Gongbo, et al.
Publicado: (2024)

Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models
por: Li, Mingda, et al.
Publicado: (2024)

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

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
por: Lee, Jinhyuk, et al.
Publicado: (2024)

Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks
por: Schelpe, Sietse
Publicado: (2026)

Distilling LLM Agent into Small Models with Retrieval and Code Tools
por: Kang, Minki, et al.
Publicado: (2025)

Big Reasoning with Small Models: Instruction Retrieval at Inference Time
por: Alkiek, Kenan, et al.
Publicado: (2025)

Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
por: Pavlidis, Nikolaos, et al.
Publicado: (2025)

Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study
por: Stolfo, Alessandro
Publicado: (2024)

What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models
por: Goworek, Roksana, et al.
Publicado: (2025)

What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques
por: Giouroukis, Petros Stylianos, et al.
Publicado: (2025)

More Room for Language: Investigating the Effect of Retrieval on Language Models
por: Samuel, David, et al.
Publicado: (2024)