mlsanityData to 7 Oct 2026

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications

arXiv 2409.09046 ↗First posted 29 Aug 2024cs.IR cs.AI cs.LGcited by 22

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs. This paper presents the Hybrid Parameter-Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case. HyPA-RAG integrates a query complexity classifier for adaptive parameter tuning, a hybrid retrieval approach combining dense, sparse, and knowledge graph methods, and a comprehensive evaluation framework with tailored question types and metrics. Testing on LL144 demonstrates that HyPA-RAG enhances retrieval accuracy, response fidelity, and contextual precision, offering a robust and adaptable solution for high-stakes legal and policy applications.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 49 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

30 of 49 references.

References · 30

  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. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  8. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  12. 2023BloombergGPT: A Large Language Model for Financecited by 923
18 more
  1. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  2. 2020Knowledge Graphscited by 619
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  4. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  5. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  6. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Modelscited by 328
  7. 2023Preference Ranking Optimization for Human Alignmentcited by 283
  8. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  9. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 170
  10. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  11. 2023Can GPT-3 Perform Statutory Reasoning?cited by 71
  12. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 55
  13. 2022Legal Prompt Engineering for Multilingual Legal Judgement Predictioncited by 54
  14. 2023A Short Survey of Viewing Large Language Models in Legal Aspectcited by 51
  15. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAGcited by 47
  16. 2021Learning to Retrieve Passages without Supervisioncited by 46
  17. 2023A Comprehensive Evaluation of Large Language Models on Legal Judgment Predictioncited by 27
  18. 2022A Study on the Efficiency and Generalization of Light Hybrid Retrieverscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 13.

22 papers.

Sort:

By area:

  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  2. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAGcited by 29
  3. 2025Towards Reliable Retrieval in RAG Systems for Large Legal Datasetscited by 12
  4. 2025Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunkingcited by 7
  5. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  6. 2025NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law Systemcited by 5
  7. 2025All for law and law for all: Adaptive RAG Pipeline for Legal Researchcited by 5
  8. 2026Revisiting RAG Retrievers: An Information Theoretic Benchmarkcited by 2
  9. 2025TAI Scan Tool: A RAG-Based Tool With Minimalistic Input for Trustworthy AI Self-Assessmentcited by 1
  10. 2026LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encodingcited by 1
  11. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAGcited by 1
  12. 2025The 3rd Place Solution of CCIR CUP 2025: A Framework for Retrieval-Augmented Generation in Multi-Turn Legal Conversationcited by 0
10 more
  1. 2026Autonomous Edge-Deployed AI Agents for Electric Vehicle Charging Infrastructure Managementcited by 0
  2. 2026Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generationcited by 0
  3. 2026PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairscited by 0
  4. 2026Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation Systemcited by 0
  5. 2026Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAGcited by 0
  6. 2026Evaluating RAG for French immigration law: a benchmark and baseline studycited by 0
  7. 2026R2Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAGcited by 0
  8. 2026Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systemscited by 0
  9. 2026FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Explorationcited by 0
  10. 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. 2026Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
  2. 2025A Reasoning-Focused Legal Retrieval Benchmark
  3. 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
  4. 2025Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India
  5. 2025Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
  6. 2025ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation
  7. 2026CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
  8. 2026Fine-grained Claim-level RAG Benchmark for Law