Knowledge Augmentation for Language Models

Follow this topic Ask about this topic

The field studies how language models can acquire and use information beyond what is already stored in their parameters, especially for changing facts, specialized domains, and multi-step tasks. Common approaches retrieve text or knowledge-graph evidence at inference time, maintain external memories, or inject knowledge through continued pretraining, supervised tuning, adapters, and synthetic data; agents may also decide when to search or use tools. Work increasingly tests not just whether evidence is available but whether models select and integrate it, using knowledge-intensive question answering, long-context, coding, medical, legal, and reasoning benchmarks. A central tension is choosing between retrieval and internalization: added context can be noisy or ignored, while weight updates can be costly and erode general abilities, so the best method depends on model scale, evidence quality, update needs, and compute.

Latest papers

180 papers18 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Can Small Language Models Use What They Retrieve? An Empirical Study of Retrieval Utilization Across Model Scale
Mar 12, 2026Sanchit PandeyRetrieval-Augmented Generation Knowledge Augmentation for Language Models
BITS Pilani, Hyderabad, India · BITS Pilani, Hyderabad Campus, Telangana, India
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
Mar 10, 2026Isabelle AugensteinKnowledge Conflicts in Language Models Factual Knowledge in Language Models
University of Copenhagen, Denmark
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Mar 9, 2026Chang Liu, Xiaoguang Li, Lifeng Shang +4Iterative RAG Question Answering
The University of Hong Kong · Huawei Noah’s Ark Lab
A Dynamic Self-Evolving Extraction System
Mar 6, 2026Moin Amin-Naseri, Hannah Kim, Estevam HruschkaDocument Information Extraction LLM Information Extraction
Megagon Labs
Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
Mar 5, 2026Hyuntae Park, Yeachan Kim, SangKeun LeeLLM Reasoning Zero-Shot Learning
Department of Artificial Intelligence, Korea University, 145 Anam-ro, Seungbuk-gu, Seoul, 02841, Republic of Korea · Department of Computer Science and Engineering, Korea University, 145 Anam-ro, Seungbuk-gu, Seoul, 02841, Republic of Korea
GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure
Mar 3, 2026Shaohuang WangKnowledge Augmentation for Language Models Knowledge-Intensive QA
FLANS at SemEval-2026 Task 7: RAG with Open-Sourced Smaller LLMs for Everyday Knowledge Across Diverse Languages and Cultures
Mar 2, 2026Liliia Bogdanova, Shiran Sun, Lifeng Han +2Multilingual QA Knowledge Augmentation for Language Models
Insilico Medicine AI Limited · University of Groningen · LIACS, Leiden University +1
Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation
Mar 1, 2026Liwen Sun, Xiang Yu, Ming Tan +4Medical LLMs Knowledge Augmentation for Language Models
Carnegie Mellon university · Amazon Health AI
Understanding LoRA as Knowledge Memory: An Empirical Analysis
Mar 1, 2026Seungju Back, Dongwoo Lee, Naun Kang +4Continual Learning for LLMs Memory-Augmented Language Models
KAIST · Samsung SDS · New York University
A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
Feb 27, 2026Zonglin Yang, Runze Mao, Tianhao Wu +3Knowledge Augmentation for Language Models LLM Evaluation
School of Mechanics and Engineering Science, Peking University, Beijing, 100871, PRChina · AI for Science Institute, Beijing, 100080, China
Decoder-based Sense Knowledge Distillation
Feb 25, 2026Qitong Wang, Mohammed J. Zaki, Georgios Kollias +1Language Model Distillation Knowledge Distillation
Rensselaer Polytechnic Institute Troy, New York, USA · IBM Research Yorktown Heights, New York, USA
Personalized Graph-Empowered Large Language Model for Proactive Information Access
Feb 25, 2026Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang +1Persistent Memory for Language Models Information Retrieval
Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan · Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Institute of Information Science, Academia Sinica, Taipei, Taiwan +1
NanoKnow: How to Know What Your Language Model Knows
Feb 23, 2026Lingwei Gu, Nour Jedidi, Jimmy LinFactual Knowledge in Language Models Language Model Pretraining
University of Waterloo Waterloo, ON, Canada
Structured Prompt Language: Declarative Context Management for LLMs
Feb 23, 2026Wen G. GongLLM Prompting LLM Context Management
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge
Feb 19, 2026Marcelo LabreRetrieval-Augmented Generation LLM Grounding
Advanced Institute for Artificial Intelligence (AI2)
Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented Generation
Feb 19, 2026Dun Yuan, Hao Zhou, Xue Liu +4Knowledge Augmentation for Language Models Graph Retrieval-Augmented Generation
Charlie · School of Computer Science, McGill University, Montreal, QC H3A 0E9, Canada. · Standards and Mobility Innovation Lab, Samsung Research America, Plano, Texas, TX 75023, USA.
Exploring LLMs for User Story Extraction from Mockups
Feb 19, 2026Diego Firmenich, Leandro Antonelli, Bruno Pazos +2Requirements Engineering Text Generation
Departamento de Informática, Facultad de Ingeniería, Universidad Nacional de la Patagonia, Argentina · LIFIA, Facultad de Informática, Universidad Nacional de La Plata, Argentina · CAETI, Facultad de Tecnología Informática - Universidad Abierta Interamericana +3
Panini: Continual Learning in Token Space via Structured Memory
Feb 16, 2026Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali +2Continual Learning for LLMs Memory-Augmented Language Models
Department of Electrical and Computer Engineering, University of California, Los Angeles, USA.
CGRA-DeBERTa Concept Guided Residual Augmentation Transformer for Theologically Islamic Understanding
Feb 16, 2026Tahir Hussain, Saddam Hussain KhanQuestion Answering Knowledge Augmentation for Language Models
Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering and Applied Sciences · Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering and Applied Sciences (UEAS), Swat, Pakistan · Interdisciplinary Research Center for Smart Mobility and Logistics +1
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
Feb 6, 2026Yewei Liu, Xiyuan Wang, Yansheng Mao +3Knowledge Augmentation for Language Models Low-Rank Adaptation
Institute for Artificial Intelligence, Peking University · School of Electronics Engineering and Computer Science, Peking University · University of Oxford +1
Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories
Feb 2, 2026Ya Gao, Kalle Kujanpää, Pekka Marttinen +2Knowledge Editing Knowledge Augmentation for Language Models
Aalto University · System 2 AI
Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
Jan 16, 2026Xin Sun, Zhongqi Chen, Qiang Liu +5Retrieval-Augmented Generation Test-Time Adaptation
NLPR, MAIS, CASIA · Ant Group · USTC
RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning
Dec 31, 2025Xiang Gao, Yuguang Yao, Qi Zhang +5Knowledge Augmentation for Language Models LLM Tool Use
1Intuit AI Research · 2Temple University
AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
Dec 18, 2025Tzu-Han Lin, Wei-Lin Chen, Chen-An Li +3Retrieval-Augmented Generation Knowledge Augmentation for Language Models
National Taiwan University · Department of Computer Science, University of Virginia
Multilingual Medical Reasoning for Question Answering with Large Language Models
Dec 5, 2025Pietro Ferrazzi, Aitor Soroa, Rodrigo AgerriKnowledge Augmentation for Language Models Healthcare
Fondazione Bruno Kessler, Trento, Italy · HiTZ Center - Ixa, University of the Basque Country EHU, Spain
Zoom In Disparities in Healthcare LLM Q&A
Oct 20, 2025Ipek Baris Schlicht, Burcu Sayin, Zhixue Zhao +5Multilingual Language Model Evaluation Knowledge Augmentation for Language Models
Universitat Politècnica de València, Valencia, Spain · University of Trento, Trento, Italy · University of Sheffield, Sheffield, UK +5
Instruction Retrieval at Inference Time for Small Language Models
Oct 15, 2025Kenan Alkiek, David Jurgens, Vinod VydiswaranKnowledge Augmentation for Language Models Small Language Models
School of Information University of Michigan Ann Arbor, MI 48109, USA
Dataset Construction for Training LLM to Learn Analog Circuit Knowledge
Aug 14, 2025Zihao Chen, Ji Zhuang, Jinyi Shen +11Language Model Pretraining Knowledge Augmentation for Language Models
Fudan University, Shanghai, China
All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
Oct 22, 2024Advait Deshmukh, Ashwin Umadi, Dananjay Srinivas +1Language Model Pretraining Long-Tail Learning
University of Colorado Boulder
FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inference
May 7, 2024Runheng Liu, Xingchen Xiao, Heyan Huang +2Knowledge Augmentation for Language Models LLM Inference Acceleration
School of Computer Science and Technology, Beijing Institute of Technology

Mar 12, 2026J/K move · Enter open · S save

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

Sanchit Pandey

BITS Pilani, Hyderabad, India · BITS Pilani, Hyderabad Campus, Telangana, India

Retrieval-Augmented Generation Knowledge Augmentation for Language Models RAG Evaluation Small Language Models

Open paper AskPDF arXiv

Retrieval augmented generation RAG is widely deployed to improve factual accuracy in language models yet it remains unclear whether smaller models of size 7B parameters or less can effectively utilize retrieved information. To investigate this question we evaluate five model sizes from 360M to 8B across three architecture families SmolLM2 Qwen2.5 and Llama 3.1 under four retrieval conditions including no retrieval BM25 dense retrieval using E5 large v2 and oracle retrieval where the retrieved passage is guaranteed to contain the answer. We introduce a parametric knowledge split that separates questions a model can already answer from those that require external knowledge which allows us to isolate utilization failure from retrieval quality failure. We find three main results. First even with oracle retrieval models of size 7B or smaller fail to extract the correct answer 85 to 100 percent of the time on questions they cannot answer alone which indicates a fundamental utilization bottleneck. Second adding retrieval context destroys 42 to 100 percent of answers the model previously knew suggesting a distraction effect driven by the presence of context rather than its quality. Third an error analysis of 2588 oracle failures shows that the dominant failure mode is irrelevant generation where the model ignores the provided context entirely. These patterns hold across multiple prompt templates and retrieval methods. The results indicate that for models below 7B parameters the main limitation of RAG is context utilization rather than retrieval quality and that deploying RAG at this scale can lead to a net negative trade off under standard evaluation conditions.