When AI output tips to bad but nobody notices: Legal implications of AI's mistakes
Authors: Dylan J. Restrepo, Nicholas J. Restrepo, Frank Y. Huo, Neil F. Johnson
Organizations: Cornell Tech, Cornell University, New York, NY 10044, USA · d-AI-ta Consulting, Delaware 19958, USA · Dynamic Online Networks Laboratory, George Washington University Washington, DC 20052, USA
The adoption of generative AI across commercial and legal professions offers dramatic efficiency gains -- yet for law in particular, it introduces a perilous failure mode in which the AI fabricates fictitious case law, statutes, and judicial holdings that appear entirely authentic. Attorneys who unknowingly file such fabrications face professional sanctions, malpractice exposure, and reputational harm, while courts confront a novel threat to the integrity of the adversarial process. This failure mode is commonly dismissed as random hallucination', but recent physics-based analysis of the Transformer's core mechanism reveals a deterministic component: the AI's internal state can cross a calculable threshold, causing its output to flip from reliable legal reasoning to authoritative-sounding fabrication. Here we present this science in a legal-industry setting, walking through a simulated brief-drafting scenario. Our analysis suggests that fabrication risk is not an anomalous glitch but a foreseeable consequence of the technology's design, with direct implications for the evolving duty of technological competence. We propose that legal professionals, courts, and regulators replace the outdated black box' mental model with verification protocols based on how these systems actually fail.
Figures & tables
Figure 1: Calculated output of the effective attention head model for the legal brief scenario. The AI’s context vector evolves with each generated token. Token selection follows the maximum dot-product rule: the AI outputs whichever content type has the largest projection onto the current context vector. Two tipping points are visible—first from neutral fact repetition (A) to correct legal analysis (B), and later from correct analysis (B) to harmful fabrication (D). All plotted values are exact arithmetic results of the model (see Appendix).
Failure Mode
Concrete Example
Professional/Rule Violation
Key Authority
B → D tipping (fabricated citation)
AI drafting a brief invents a case and holding to support a tolling argument.
Attorneys, judges, and pro se filers increasingly use AI to draft legal documents, yet these tools frequently fabricate citations. Despite predictions that newer models would hallucinate less or that court sanctions would deter negligent filers, we found over 1,000 filings containing fabricated citations---with this number growing year-over-year. This study evaluates whether AI-based systems can mitigate these errors by automatically detecting hallucinations. We propose a taxonomy of legal citation hallucinations grounded in actual court filings and introduce a dataset of 1,300 brief excerpts containing injected errors. Benchmarking five models in agentic and non-agentic settings as well as Claude Code reveals that while the latest iterations perform better---GPT-5 achieves 84.4% recall and a 55.0% F1 score in an agentic framework---all models struggle with subtle error categories. Agentic verification remains resource-intensive, with GPT-5 averaging 15.3 steps per excerpt. Furthermore, restricted information access limits the efficacy of even the best agents. This gap creates policy concerns, as it disadvantages both AI systems and litigants who lack subscriptions to commercial legal databases. Together, our dataset, tools, and policy recommendations provide a foundation for building and auditing reliable legal citation checking tools.
Integrating Large Language Models (LLMs) into the Indian judiciary promises access to justice but introduces severe risks. We identify the 'inertia of confidence'--an overconfidence phenomenon analogous to the Dunning-Kruger effect where LLMs provide incorrect legal verdicts with near-maximum confidence, driven by a hypothesized 'precedent overfitting' bias. Phase I of our socio-technical audit tested ChatGPT (GPT-5.2), Meta AI, and Perplexity AI on a 60-case battery regarding the Indian Contract Act, 1872, and the shift toward statutory enforcement of specific performance. We introduce the High-Confidence Error Rate (HCER) to quantify incorrect verdicts delivered with dangerous certainty (>= 9 on a 1-10 scale). All models struggled with statutory updates. Meta AI proved most vulnerable (31.7% HCER), frequently misapplying pre-amendment rules with a 9.1/10 mean confidence, followed by Perplexity (15.0%) and ChatGPT (6.7%). Phase II investigated human vulnerability to this overconfidence via a survey of Indian law students (N=380). Verification often functions as a reactive adaptation to machine hallucinations: students encountering fabricated citations reported higher verification scores (4.2/5) than those with no such encounters (2.8/5). Furthermore, while 81.6% knew submitting hallucinated cases can lead to contempt-of-court, 71.1% received no formal training on ethical AI use. We propose shifting toward adversarial legal research pedagogy and implementing source-grounded verification architectures to prevent systemic professional negligence.
Angel Mary John, Vipin Kumar Singh, Jerrin Thomas Panachakel
Department of Law Sunrise University Alwar, Rajasthan, India · School of Electrical and Electronic Engineering Technological University Dublin Dublin, Ireland
AI systems deployed in legal workflows hallucinate at rates that aggregate metrics report at ~52%, but this average conceals where errors concentrate and in which direction they run, leaving compliance officers without an actionable signal for trustworthy deployment. We present LegalHalluLens, an auditing framework with three components: typed hallucination profiles across four legally-motivated claim categories (numeric, temporal, obligation/entitlement, factual) over CUAD (Hendrycks et al., 2021); a Risk Direction Index (RDI) that reduces omission-versus-invention bias to a single deployment-comparable scalar; and a typed debate pipeline calibrated to both magnitudes and directions. Across 510 contracts and 249,252 clause-level instances we measure a within-model gap of approximately 38-40 pp between obligation/numeric and temporal claims that aggregate reporting hides, and show that two systems with matched 52% rates can carry opposite RDIs. The debate pipeline reduces fabricated detections by 45% with per-category gains tracking the diagnosis, matching commercial APIs with a substantially smaller backbone (4B active parameters). Typed profiles and RDI surface failure modes that aggregate metrics hide; we further show these diagnostics serve as calibration inputs for multi-agent debate pipelines, where Skeptic challenges and asymmetric gates targeted at measured failure modes outperform generically-tuned debate. The framework supports direction-aware procurement, accountability, and agent design for legal AI deployed in the wild.
Lalit Yadav, Akshaj Gurugubelli
Independent Researcher, Sunnyvale, CA, USA · Independent Researcher, San Diego, CA, USA