mlsanityData to 14 Oct 2026

Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders

arXiv 2604.07825 ↗First posted 9 Apr 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have recently emerged as powerful training-free recommenders. However, their knowledge of individual items is inevitably uneven due to imbalanced information exposure during pretraining, a phenomenon we refer to as knowledge gap problem. To address this, most prior methods have employed a naive uniform augmentation that appends external information for every item in the input prompt. However, this approach not only wastes limited context budget on redundant augmentation for well-known items but can also hinder the model's effective reasoning. To this end, we propose KnowSACKP (Knowledge-aware Selective Augmentation with Comparative Knowledge Probing) to mitigate the knowledge gap problem. KnowSACKP estimates the LLM's internal knowledge by evaluating its capability to capture collaborative relationships and selectively injects additional information only where it is most needed. By avoiding unnecessary augmentation for well-known items, KnowSACKP focuses on items that benefit most from knowledge supplementation, thereby making more effective use of the context budget. KnowSACKP requires no fine-tuning step, and consistently improves both recommendation accuracy and context efficiency across four real-world datasets. Our code is available at https://github.com/nowhyun/KnowSACKP.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

39 of 54 references.

References · 39

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2020Extracting Training Data from Large Language Modelscited by 2,189
  6. 2018Self-Attentive Sequential Recommendationcited by 1,184
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2023Active Retrieval Augmented Generationcited by 516
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  10. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  11. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 309
  12. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
27 more
  1. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  2. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  3. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 150
  4. 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 104
  5. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 82
  6. 2023Leveraging Large Language Models for Sequential Recommendationcited by 78
  7. 2023ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendationcited by 77
  8. 2023A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systemscited by 73
  9. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  10. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendationcited by 57
  11. 2024Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Methodcited by 55
  12. 2023LlamaRec: Two-Stage Recommendation using Large Language Models for Rankingcited by 53
  13. 2024Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender Systemcited by 50
  14. 2023Characterizing Mechanisms for Factual Recall in Language Modelscited by 48
  15. 2024LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendationcited by 47
  16. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  17. 2024Harnessing Large Language Models for Text-Rich Sequential Recommendationcited by 38
  18. 2023RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendationcited by 36
  19. 2023Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendationcited by 29
  20. 2024Text-like Encoding of Collaborative Information in Large Language Models for Recommendationcited by 25
  21. 2024Review-driven Personalized Preference Reasoning with Large Language Models for Recommendationcited by 22
  22. 2019Candidate Generation with Binary Codes for Large-Scale Top-N Recommendationcited by 19
  23. 2024A Queueing Theoretic Perspective on Low-Latency LLM Inference with Variable Token Lengthcited by 16
  24. 2024Taxonomy-Guided Zero-Shot Recommendations with LLMscited by 15
  25. 2024Enhancing Sequential Music Recommendation with Personalized Popularity Awarenesscited by 7
  26. 2024DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systemscited by 6
  27. 2025ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendationcited by 2

Built on by

Not cited yet.