Why Avoid Generative Legal AI Systems? Hallucination, Overreliance, and their Impact on Explainability

• URL: http://arxiv.org/abs/2603.15937v1
• Date: Mon, 16 Mar 2026 21:40:43 GMT
• Title: Why Avoid Generative Legal AI Systems? Hallucination, Overreliance, and their Impact on Explainability
• Abstract summary: This article argues that the deployment of generative AI systems in legal profession requires strong restraint due to the critical risks of hallucination and overreliance.<n>Central to this analysis is the definition of Generative Legal AI (GLAI), an umbrella term for systems specifically adapted for the legal domain.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This article argues that the deployment of generative AI systems in legal profession requires strong restraint due to the critical risks of hallucination and overreliance. Central to this analysis is the definition of Generative Legal AI (GLAI), an umbrella term for systems specifically adapted for the legal domain which is ranging from document drafting to decision support in criminal justice. Unlike traditional AI, GLAI models are built on architectures designed for statistical token prediction rather than legal reasoning, often leading to confabulations where the system prioritizes linguistic fluency over factual accuracy. These hallucinations obscure the reasoning process, while the persuasive, human-like nature of the output encourages professional overreliance. The paper situates these dynamics within the framework of European AI governance, arguing that the interaction between fabricated data and automation bias fundamentally weakens the principle of explainability. The article concludes that without effective mechanisms for meaningful human scrutiny, the routine adoption of GLAI poses significant challenges to judicial independence and the protection of fundamental rights.

Related papers

• Validity, Reliability, and Transparency in Artificial Intelligence Regulation [2.588958866512272]
  Article argues that modern AI raises concerns of construct validity, confounding, representativeness, distribution shift, and fairness trade-offs.<n>We argue that inference should function as a precondition for proportionality assessment and deployment approval.
  arXiv  Detail & Related papers  (2026-08-06T09:36:15Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning [3.093890460224435]
  The growing adoption of large language models in legal practice brings both significant promise and serious risk.<n>This proposal presents a neuro-symbolic approach to legal AI that combines the expressive power of large language models with the rigor of formal verification.
  arXiv  Detail & Related papers  (2026-05-13T19:11:09Z)
• Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution [80.98492754957466]
  Core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously.<n>This paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI.
  arXiv  Detail & Related papers  (2026-05-04T14:26:28Z)
• Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections [53.468443050795344]
  The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape.<n>As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to articulate regulatory stipulations.<n>This paper reviews the evolving European Union (EU) AI regulatory provisions via analyzing 24 relevant documents published between 2024 and 2025.
  arXiv  Detail & Related papers  (2026-03-19T13:50:52Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• From Abstract Threats to Institutional Realities: A Comparative Semantic Network Analysis of AI Securitisation in the US, EU, and China [0.0]
  Major jurisdictions converge rhetorically around concepts such as safety, risk, and accountability, but their regulatory frameworks remain fundamentally divergent and mutually unintelligible.<n>This paper argues that this fragmentation cannot be explained solely by geopolitical rivalry, institutional complexity, or instrument selection.<n>Using semantic network analysis, we trace how concepts like safety are embedded within divergent semantic architectures.
  arXiv  Detail & Related papers  (2026-01-07T17:12:03Z)
• Judicial Requirements for Generative AI in Legal Reasoning [0.0]
  Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in high-stakes fields like law remain poorly understood.<n>This paper defines the core capabilities that an AI system must possess to function as a reliable reasoning tool in judicial decision-making.
  arXiv  Detail & Related papers  (2025-08-26T09:56:26Z)
• GLARE: Agentic Reasoning for Legal Judgment Prediction [60.13483016810707]
  Legal judgment prediction (LJP) has become increasingly important in the legal field.<n>Existing large language models (LLMs) have significant problems of insufficient reasoning due to a lack of legal knowledge.<n>We introduce GLARE, an agentic legal reasoning framework that dynamically acquires key legal knowledge by invoking different modules.
  arXiv  Detail & Related papers  (2025-08-22T13:38:12Z)
• A Conjecture on a Fundamental Trade-Off between Certainty and Scope in Symbolic and Generative AI [0.0]
  Article introduces a conjecture that formalises a fundamental trade-off between provable correctness and broad data-mapping capacity in AI systems.<n>By making this implicit trade-off explicit and open to rigorous verification, the conjecture significantly reframes both engineering ambitions and philosophical expectations for AI.
  arXiv  Detail & Related papers  (2025-06-11T19:18:13Z)
• The Fundamental Rights Impact Assessment (FRIA) in the AI Act: Roots, legal obligations and key elements for a model template [55.2480439325792]
  Article aims to fill existing gaps in the theoretical and methodological elaboration of the Fundamental Rights Impact Assessment (FRIA)<n>This article outlines the main building blocks of a model template for the FRIA.<n>It can serve as a blueprint for other national and international regulatory initiatives to ensure that AI is fully consistent with human rights.
  arXiv  Detail & Related papers  (2024-11-07T11:55:55Z)
• Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making [69.44075077934914]
  "Responsible AI" emphasizes the critical nature of addressing biases within the development of a corporate culture. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages.
  arXiv  Detail & Related papers  (2024-01-13T14:07:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.