Image de couverture de livre

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Hanbing, Cao, Lang, Li, Yang
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TableMaster: A Recipe to Advance Table Understanding with Language Models
par: Cao, Lang, et autres
Publié: (2025)

Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism
par: Cao, Lang
Publié: (2023)

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
par: Liu, Hanbing, et autres
Publié: (2025)

Understanding Knowledge Drift in LLMs through Misinformation
par: Fastowski, Alina, et autres
Publié: (2024)

KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge
par: Jiang, Pengcheng, et autres
Publié: (2024)

Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation
par: Muttakhiroh, Iing, et autres
Publié: (2025)

KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
par: Li, Yongjian, et autres
Publié: (2025)

From Task Solving to Robust Real-World Adaptation in LLM Agents
par: Pezeshkpour, Pouya, et autres
Publié: (2026)

CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge
par: Bae, Seyun, et autres
Publié: (2026)

Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAG
par: Drole, Jan, et autres
Publié: (2026)

Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning
par: Ren, Jingyi, et autres
Publié: (2025)

KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs
par: Wu, Dingjun, et autres
Publié: (2025)

KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities
par: Markondapatnaikuni, Hruday, et autres
Publié: (2025)

A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
par: Xie, Yangxinyu, et autres
Publié: (2025)

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
par: Jiang, Pengcheng, et autres
Publié: (2025)

DiagGPT: An LLM-based and Multi-agent Dialogue System with Automatic Topic Management for Flexible Task-Oriented Dialogue
par: Cao, Lang
Publié: (2023)

Orthogonal Low-rank Adaptation in Lie Groups for Continual Learning of Large Language Models
par: Cao, Kefan, et autres
Publié: (2025)

ExpWeaver: LLM Agents Learn from Experience via Latent RAG
par: Feng, Tao, et autres
Publié: (2026)

ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding
par: Li, Xiaozhe, et autres
Publié: (2025)

HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings
par: Gumma, Varun, et autres
Publié: (2024)

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
par: Xu, Frank F., et autres
Publié: (2024)

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
par: Zhang, Yuji, et autres
Publié: (2025)

LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
par: Sourati, Zhivar, et autres
Publié: (2025)

Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning
par: Ren, Houxing, et autres
Publié: (2026)

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
par: Jin, Zhuoran, et autres
Publié: (2024)

Domain-Specific Data Generation Framework for RAG Adaptation
par: Tian, Chris Xing, et autres
Publié: (2025)

Real-World Summarization: When Evaluation Reaches Its Limits
par: Schmidtová, Patrícia, et autres
Publié: (2025)

CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher
par: Liu, Tianlun, et autres
Publié: (2025)

Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework
par: Narita, Kenichirou, et autres
Publié: (2026)

Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning
par: Huo, Nan, et autres
Publié: (2025)

WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario
par: Zhang, Jiebin, et autres
Publié: (2024)

FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol
par: Zhu, Jie, et autres
Publié: (2026)

Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
par: Wu, Keshu, et autres
Publié: (2026)

ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
par: Wang, Chenyu, et autres
Publié: (2026)

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?
par: Wang, Haoxin, et autres
Publié: (2025)

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation
par: Zhao, Jingqian, et autres
Publié: (2025)

Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
par: Wang, Xudong, et autres
Publié: (2026)

Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
par: Lin, Junhong, et autres
Publié: (2025)

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
par: Bañeras-Roux, Thibault, et autres
Publié: (2026)

ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
par: Singh, Ishneet Sukhvinder, et autres
Publié: (2024)