mlsanityData to 7 Oct 2026

RAGSys: Item-Cold-Start Recommender as RAG System

arXiv 2405.17587 ↗First posted 27 May 2024cs.IR cs.CL cs.LGcited by 4

On the map: Retrieval-augmented generation → RAG for recommendation

Abstract (arXiv)

Large Language Models (LLM) hold immense promise for real-world applications, but their generic knowledge often falls short of domain-specific needs. Fine-tuning, a common approach, can suffer from catastrophic forgetting and hinder generalizability. In-Context Learning (ICL) offers an alternative, which can leverage Retrieval-Augmented Generation (RAG) to provide LLMs with relevant demonstrations for few-shot learning tasks. This paper explores the desired qualities of a demonstration retrieval system for ICL. We argue that ICL retrieval in this context resembles item-cold-start recommender systems, prioritizing discovery and maximizing information gain over strict relevance. We propose a novel evaluation method that measures the LLM's subsequent performance on NLP tasks, eliminating the need for subjective diversity scores. Our findings demonstrate the critical role of diversity and quality bias in retrieved demonstrations for effective ICL, and highlight the potential of recommender system techniques in this domain.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 54 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

26 of 54 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  9. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  10. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  12. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
14 more
  1. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  2. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  3. 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selectioncited by 291
  4. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  5. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 215
  6. 2022In-context Examples Selection for Machine Translationcited by 172
  7. 2023Compositional Exemplars for In-context Learningcited by 143
  8. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  9. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  10. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  11. 2023Learning to Retrieve In-Context Examples for Large Language Modelscited by 60
  12. 2013Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Explorationcited by 50
  13. 2021DGCN: Diversified Recommendation with Graph Convolutional Networkscited by 29
  14. 2024LLM In-Context Recall is Prompt Dependentcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systemscited by 9
  2. 2026Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesiscited by 3
  3. 2024ICLERB: In-Context Learning Embedding and Reranker Benchmarkcited by 1
  4. 2025POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applicationscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
  2. 2025A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
  3. 2025RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning
  4. 2025WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web
  5. 2025Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
  6. 2024Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
  7. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  8. 2025RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning