mlsanityData to 14 Oct 2026

A Multi-Task Embedder For Retrieval Augmented LLMs

arXiv 2310.07554 ↗First posted 11 Oct 2023cs.IRcited by 64

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

Abstract (arXiv)

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the LLM. However, existing retrieval methods encounter two pressing issues. On one hand, the general retrievers are not properly optimized for retrieval augmentation hence exhibit limited effectiveness; on the other hand, the task-specific retrievers excel in the targeted retrieval augmentation scenario, while lack the versatility to handle diverse scenarios. In this work, we propose LLM-Embedder for the unified support of diverse retrieval augmentation scenarios. Our method presents three technical contributions. Firstly, we introduce a new textitreward formulation, namely rank-aware reward. It exploits the ranking position of the desired output among N sampled outputs from the LLM, which leads to fine-grained and robust computation of reward from the LLM's feedback. Secondly, we design a novel textitdistillation objective, called graded distillation. It incorporates both the absolute value and the relative order of the reward for more sufficient utilization of the LLM's feedback. Thirdly, we systematically optimize the textitmulti-task learning, which effectively unifies the multiple retrieval functionalities into one model. In our experiment, LLM-Embedder notably improves the LLM's performances in various downstream tasks, and outperforms both general and task-specific retrievers with a substantial advantage.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 50 of its 87 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

50 of 87 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan
  2. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug

Other references · 48

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  10. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  11. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  12. 2017Billion-scale similarity search with GPUscited by 2,497
36 more
  1. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  3. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  6. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  9. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  10. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  12. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  13. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  14. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  15. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
  16. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  17. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413
  18. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  19. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  20. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 333
  21. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  22. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  23. 2023L-Eval: Instituting Standardized Evaluation for Long Context Language Modelscited by 233
  24. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  25. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 148
  26. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  27. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  28. 2022SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrievalcited by 90
  29. 2021Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challengecited by 80
  30. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
  31. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  32. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  33. 2019This Email Could Save Your Life: Introducing the Task of Email Subject Line Generationcited by 58
  34. 2021UDALM: Unsupervised Domain Adaptation through Language Modelingcited by 33
  35. 2022Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddingscited by 17
  36. 2017Efficient Twitter Sentiment Classification using Subjective Distant Supervisioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 38; 2025: 19; 2026: 5.

64 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  3. 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 109
  4. 2024Towards Building Multilingual Language Model for Medicinecited by 92
  5. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  6. 2024MegaPairs: Massive Data Synthesis For Universal Multimodal Retrievalcited by 84
  7. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  8. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  9. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  10. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 66
  11. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  12. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 48
38 more
  1. 2024GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuningcited by 40
  2. 2024AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMscited by 36
  3. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
  4. 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Modelscited by 27
  5. 2024KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checkingcited by 26
  6. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoningcited by 26
  7. 2024AesopAgent: Agent-driven Evolutionary System on Story-to-Video Productioncited by 13
  8. 2024Towards LifeSpan Cognitive Systemscited by 13
  9. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generationcited by 12
  10. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecastingcited by 12
  11. 2024Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Studycited by 11
  12. 2026Agentic-R: Learning to Retrieve for Agentic Searchcited by 11
  13. 2025The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systemscited by 10
  14. 2024Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimizationcited by 9
  15. 2024MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generationcited by 8
  16. 2025AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoningcited by 8
  17. 2024Reward-RAG: Enhancing RAG with Reward Driven Supervisioncited by 7
  18. 2024What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysiscited by 7
  19. 2025Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generationcited by 7
  20. 2025RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practicecited by 6
  21. 2025Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domaincited by 6
  22. 2024API Pack: A Massive Multi-Programming Language Dataset for API Call Generationcited by 5
  23. 2024AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistantcited by 5
  24. 2024Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systemscited by 4
  25. 2025Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generationcited by 4
  26. 2026Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interactioncited by 4
  27. 2024Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Stepscited by 3
  28. 2024Invar-RAG: Invariant LLM-aligned Retrieval for Better Generationcited by 3
  29. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
  30. 2024Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMscited by 2
  31. 2024FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understandingcited by 2
  32. 2024Autoencoder-based General Purpose Representation Learning for Customer Embeddingcited by 1
  33. 2024Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generationcited by 1
  34. 2024Investigating Distributions of Telecom Adapted Sentence Embeddings for Document Retrievalcited by 1
  35. 2024Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Eventscited by 1
  36. 2024Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generationcited by 1
  37. 2025SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Modelscited by 1
  38. 2025DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generationcited by 1

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval
  2. 2026Aligning Dense Retrievers with LLM Utility via Distillation
  3. 2025Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
  4. 2025ELITE: Embedding-Less retrieval with Iterative Text Exploration
  5. 2026Learning to Retrieve via Reinforcement Learning in Embedding Space
  6. 2024Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
  7. 2026Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families
  8. 2025Multi-task retriever fine-tuning for domain-specific and efficient RAG