mlsanityData to 7 Oct 2026

Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act

arXiv 2606.20359 ↗First posted 18 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-represented tenants, landlords, and help-desk staff need to be pointed at the provision of law that actually governs a question, with a correct statutory citation. We study this task on the Ontario Residential Tenancies Act, 2006 (RTA) and its core regulation, asking the operator's question empirically: is fine-tuning enough, or is hybrid retrieval needed? We run a four-arm head-to-head on Qwen2.5-7B-Instruct (base zero-shot, LoRA SFT-only, RAG-only, and an SFT+RAG hybrid), scored on citation exact-match (section+subsection) over a small, human-verification-pending real eval set. The base model cannot cite the RTA and SFT-only mis-recalls sections; retrieval is essential and drives hallucination to zero by construction; and the SFT+RAG hybrid scores highest at 0.481 exact-match with zero hallucinated citations. Its edge comes from SFT making provision selection more robust to the higher-recall candidate sets that hurt zero-shot RAG. Notably, this cheap bge-small hybrid matches or beats a pipeline built on bigger, specialized retrieval models (a larger embedder and a cross-encoder reranker), and a larger/improved training set does not help either: strong statutory-citation performance here does not require specialized retrieval models or more data. The artifact zeroes hallucination and clears the lift-over-base bar but does not reach the aspirational 0.70 exact-match target. All results are on a small, human-verification-pending real eval set and are reported as preliminary.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 18 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

17 of 18 references.

References · 17

  1. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  2. 2024CaLM: Contrasting Large and Small Language Models to Verify Grounded Generationcited by 11
  3. 2025LawPal : A Retrieval Augmented Generation Based System for Enhanced Legal Accessibility in Indiacited by 6
  4. 2025LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrievalcited by 5
  5. 2025NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law Systemcited by 5
  6. 2025IL-PCSR: Legal Corpus for Prior Case and Statute Retrievalcited by 5
  7. 2024TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMscited by 4
  8. 2025Learning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning?cited by 4
  9. 2025How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustnesscited by 4
  10. 2025Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Contextcited by 2
  11. 2024Judgement Citation Retrieval using Contextual Similaritycited by 1
  12. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 1
5 more
  1. 2025Segment First, Retrieve Better: Realistic Legal Search via Rhetorical Role-Based Queriescited by 1
  2. 2025Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrievalcited by 1
  3. 2025Attribution-Guided Decodingcited by 1
  4. 2025HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignmentcited by 1
  5. 2026Suppressing Domain-Specific Hallucination in Construction LLMs: A Knowledge Graph Foundation for GraphRAG and QLoRA on River and Sediment Control Technical Standardscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law
  2. 2026Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain
  3. 2026Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment
  4. 2026Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
  5. 2026Fine-grained Claim-level RAG Benchmark for Law
  6. 2026Building Legal Reward Models for Grounding and Abstention
  7. 2025Towards Reliable Retrieval in RAG Systems for Large Legal Datasets
  8. 2026Benchmarking Legal RAG: The Promise and Limits of AI Statutory Surveys