mlsanityData to 14 Oct 2026

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter

arXiv 2310.18347 ↗First posted 23 Oct 2023cs.CLcited by 38

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to be fine-tuned with budget constraints while some of them are only accessible via APIs. To tackle this issue and further improve ReQA performance, we propose a trainable Pluggable Reward-Driven Contextual Adapter (PRCA), keeping the generator as a black box. Positioned between the retriever and generator in a Pluggable manner, PRCA refines the retrieved information by operating in a token-autoregressive strategy via maximizing rewards of the reinforcement learning phase. Our experiments validate PRCA's effectiveness in enhancing ReQA performance on three datasets by up to 20% improvement to fit black-box LLMs into existing frameworks, demonstrating its considerable potential in the LLMs era.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 36 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

30 of 36 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  8. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  10. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  11. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
18 more
  1. 2020Learning to summarize from human feedbackcited by 2,588
  2. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  9. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  13. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  14. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  15. 2023DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scalescited by 108
  16. 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 96
  17. 2021RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarizationcited by 19
  18. 2019Improving Question Answering with External Knowledgecited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 19; 2025: 13; 2026: 4.

38 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
  3. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  4. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  5. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  6. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 66
  7. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  8. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  9. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  10. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 30
  11. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidencecited by 28
  12. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
26 more
  1. 2024A Survey of Conversational Searchcited by 22
  2. 2024Characterizing Prompt Compression Methods for Long Context Inferencecited by 18
  3. 2024An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generationcited by 16
  4. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilitiescited by 16
  5. 2025GINGER: Grounded Information Nugget-Based Generation of Responsescited by 16
  6. 2025Hierarchical Document Refinement for Long-context Retrieval-augmented Generationcited by 16
  7. 2025Long Context In-Context Compression by Getting to the Gist of Gistingcited by 13
  8. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
  9. 2024Preference-Guided Refactored Tuning for Retrieval Augmented Code Generationcited by 10
  10. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  11. 2025SCOPE: A Generative Approach for LLM Prompt Compressioncited by 6
  12. 2024UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Modelscited by 5
  13. 2025CompLLM: Compression for Long Context Q&Acited by 5
  14. 2025Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generationcited by 4
  15. 2024Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Modelscited by 3
  16. 2024LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Modelscited by 2
  17. 2025K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressorcited by 2
  18. 2025Addressing the sustainable AI trilemma: a case study on LLM agents and RAGcited by 1
  19. 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generationcited by 1
  20. 2025UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responsescited by 1
  21. 2026MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generationcited by 1
  22. 2025FB-RAG: Improving RAG with Forward and Backward Lookupcited by 0
  23. 2025Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentationscited by 0
  24. 2026Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Surveycited by 0
  25. 2026Learning What to Remember: Long-horizon Counterfactual Memory Optimizationcited by 0
  26. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
  2. 2023Query Rewriting for Retrieval-Augmented Large Language Models
  3. 2023BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer
  4. 2024Retrieval Augmented Generation for Domain-specific Question Answering
  5. 2025Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k
  6. 2025ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
  7. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration
  8. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering