Cover Image

Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hamdani, Rajaa El, Haffoudhi, Samy, Holzenberger, Nils, Suchanek, Fabian, Bonald, Thomas, Malliaros, Fragkiskos D.
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Factuality of Large Language Models in the Legal Domain
by: Hamdani, Rajaa El, et al.
Published: (2024)

LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation
by: Haffoudhi, Samy, et al.
Published: (2026)

LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation
by: Haffoudhi, Samy, et al.
Published: (2026)

FLORA: Unsupervised Knowledge Graph Alignment by Fuzzy Logic
by: Peng, Yiwen, et al.
Published: (2025)

Language Models and Logic Programs for Trustworthy Tax Reasoning
by: Jurayj, William, et al.
Published: (2025)

Refining Wikidata Taxonomy using Large Language Models
by: Peng, Yiwen, et al.
Published: (2024)

YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
by: Suchanek, Fabian, et al.
Published: (2023)

BLT: Can Large Language Models Handle Basic Legal Text?
by: Blair-Stanek, Andrew, et al.
Published: (2023)

Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
by: Attali, Hugo, et al.
Published: (2025)

Uplift Modeling Under Limited Supervision
by: Panagopoulos, George, et al.
Published: (2024)

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
by: Yu, Haeun, et al.
Published: (2024)

Continuous Product Graph Neural Networks
by: Einizade, Aref, et al.
Published: (2024)

Piecewise Constant Spectral Graph Neural Network
by: Martirosyan, Vahan, et al.
Published: (2025)

Reframing Tax Law Entailment as Analogical Reasoning
by: Zou, Xinrui, et al.
Published: (2024)

OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
by: Blair-Stanek, Andrew, et al.
Published: (2023)

Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation
by: Chhun, Cyril, et al.
Published: (2024)

Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
by: Vazhentsev, Artem, et al.
Published: (2026)

Generating Tables from the Parametric Knowledge of Language Models
by: Berkovitch, Yevgeni, et al.
Published: (2024)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2024)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2026)

Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
by: Tan, Yuqiao, et al.
Published: (2025)

Linearly Decoding Refused Knowledge in Aligned Language Models
by: Shrivastava, Aryan, et al.
Published: (2025)

From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
by: Li, Lei, et al.
Published: (2025)

CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
by: Jiang, Yi, et al.
Published: (2025)

Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
by: Nemkova, Apollinaire Poli, et al.
Published: (2025)

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
by: Kim, Minsung, et al.
Published: (2025)

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
by: Nguyen, Ngoc Trinh Hung, et al.
Published: (2026)

Evaluating the External and Parametric Knowledge Fusion of Large Language Models
by: Zhang, Hao, et al.
Published: (2024)

Flexible and Efficient Grammar-Constrained Decoding
by: Park, Kanghee, et al.
Published: (2025)

BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&A
by: Ateia, Samy, et al.
Published: (2024)

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
by: Wang, Ziyao, et al.
Published: (2025)

A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning
by: Sangare, Amadou S., et al.
Published: (2025)

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
by: Fisher, Jillian, et al.
Published: (2024)

Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
by: Tu, Lifu, et al.
Published: (2023)

MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification
by: Helwe, Chadi, et al.
Published: (2023)

Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
by: Karim, A H M Rezaul, et al.
Published: (2026)

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
by: Fang, Junfeng, et al.
Published: (2024)

LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation
by: Sun, Yang, et al.
Published: (2025)

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
by: Tan, Yuqiao, et al.
Published: (2025)

A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge
by: Song, Jongyoon, et al.
Published: (2025)