mlsanityData to 7 Oct 2026

Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning

arXiv 2402.12177 ↗First posted 19 Feb 2024cs.LG cs.AI cs.CLcited by 2

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Retrieval Augmented Generation (RAG) has emerged as an effective solution for mitigating hallucinations in Large Language Models (LLMs). The retrieval stage in RAG typically involves a pre-trained embedding model, which converts queries and passages into vectors to capture their semantics. However, a standard pre-trained embedding model may exhibit sub-optimal performance when applied to specific domain knowledge, necessitating fine-tuning. This paper addresses scenarios where the embeddings are only available from a black-box model. We introduce Model augmented fine-tuning (Mafin) -- a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model. Our results demonstrate that Mafin significantly enhances the performance of the black-box embeddings by only requiring the training of a small augmented model. We validate the effectiveness of our method on both labeled and unlabeled datasets, illustrating its broad applicability and efficiency.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 35 of its 54 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

35 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Active Retrieval Augmented Generation11 May
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2023Let's Verify Step by Stepcited by 3,598
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  10. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  12. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
20 more
  1. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  3. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  4. 2022MTEB: Massive Text Embedding Benchmarkcited by 623
  5. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  6. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
  7. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  8. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 175
  9. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  10. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  11. 2024RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculturecited by 80
  12. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  13. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  14. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  15. 2018Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memorycited by 49
  16. 2018End-to-End Retrieval in Continuous Spacecited by 46
  17. 2019Conversing by Reading: Contentful Neural Conversation with On-demand Machine Readingcited by 32
  18. 2020MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Modelscited by 23
  19. 2020Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memorycited by 22
  20. 2022Exploring Dual Encoder Architectures for Question Answeringcited by 19

Built on by

Cited by year

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

2 papers.

  1. 2024QAEncoder: Towards Aligned Representation Learning in Question Answering Systemscited by 3
  2. 2025Domain-Specific Data Generation Framework for RAG Adaptationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
  2. 2025LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing
  3. 2024Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
  4. 2025ELITE: Embedding-Less retrieval with Iterative Text Exploration
  5. 2025Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG
  6. 2026Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models
  7. 2024Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems
  8. 2025Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation