# Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain arXiv: https://arxiv.org/abs/2606.09724 ยท HTML: https://mlsanity.com/paper/2606.09724/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. - Builds on 27 of its 59 references that are in the map. - First posted on arXiv 8 Jun 2026. ## Placed in - Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/) ## Builds on (most cited first, 27 of 27) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023) - [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024) - [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023) - [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024) - [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023) - [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023) - [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024) - [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024) - [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024) - [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024) - [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024) - [SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval](https://mlsanity.com/paper/2304.11370/) (2023) - [EventKG: A Multilingual Event-Centric Temporal Knowledge Graph](https://mlsanity.com/paper/1804.04526/) (2018) - [SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain](https://mlsanity.com/paper/2407.19584/) (2024) - [A Reasoning-Focused Legal Retrieval Benchmark](https://mlsanity.com/paper/2505.03970/) (2025) - [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024) - [OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models](https://mlsanity.com/paper/2412.15235/) (2024) - [Towards Reliable Retrieval in RAG Systems for Large Legal Datasets](https://mlsanity.com/paper/2510.06999/) (2025) - [Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks](https://mlsanity.com/paper/2301.12847/) (2023) - [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025) - [Unlocking Legal Knowledge with Multi-Layered Embedding-Based Retrieval](https://mlsanity.com/paper/2411.07739/) (2024) - [An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach](https://mlsanity.com/paper/2505.00039/) (2025) - [Modeling the Diachronic Evolution of Legal Norms: An LRMoo-Based, Component-Level, Event-Centric Approach to Legal Knowledge Graphs](https://mlsanity.com/paper/2506.07853/) (2025) - [Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2510.06002/) (2025) - [Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge](https://mlsanity.com/paper/2604.14488/) (2026) ## Abstract (arXiv) Retrieval-Augmented Generation (RAG) has become a standard architectural response to unreliability in legal AI, yet high-profile failures, including fabricated citations submitted to courts and anachronistic legal content presented as current, continue to appear across jurisdictions. We argue that these failures are not residual confabulations to be eliminated by scaling language models, but symptoms of an architectural mismatch between probabilistic retrieval and the hierarchical, temporal, and institutional structure of legal knowledge. We develop the argument in three moves. First, we articulate the ontological commitment of legal knowledge as a triad of properties derivable from classical legal theory: hierarchical and mereological structure, diachronic dynamism under operational closure, and causal traceability of institutional provenance grounded in the duty of justification. Second, we identify three corresponding pathologies of retrieval (mereological blindness, diachronic blindness, and causal opacity), each developed with an operational definition, a failure mechanism, a canonical example, and detection criteria for diagnostic use. Third, we review the state of the art through this lens, showing that existing approaches address these requirements unevenly and do not yet compose into a paradigm that treats them as co-constitutive. From this analysis we derive four architectural commitments that characterize the deterministic-by-design direction for legal retrieval: ontological primacy, event reification, bitemporal correctness, and deterministic interaction protocols. The framework concerns quaestio juris (which norms apply and in what state) rather than the downstream tasks that act on identified norms, and addresses legislative and constitutional retrieval primarily, with interpretive time as an explicit extension.