Local LLM for legal-document adaptation keeps hallucinating citations with total confidence — grounding/model/pipeline ideas?
Summary
A user reports that a local LLM hallucinates citations with high confidence when adapted for legal documents, and seeks advice on grounding, model, or pipeline ideas to mitigate this issue.
Similar Articles
When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection
The paper introduces PARCEL, a claim-level benchmark for detecting legal hallucinations in LLM output, using 3,396 parenthetical-style claims from New York State Court of Appeals decisions framed as three-way NLI. State-of-the-art LLMs reach up to 0.97 accuracy zero-shot but still mislabel unsupported claims as supported, especially with fabricated yet plausible citations.
Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment
This paper investigates whether standard benchmarks underestimate LLM performance by re-evaluating hallucination detection datasets using an LLM-first, human-adjudicated assessment method. The study finds that incorporating LLM reasoning into the adjudication process improves agreement and suggests that model-assisted re-evaluation yields more reliable benchmarks for ambiguity-prone tasks.
We’ve been analyzing how people are using LLMs for legal and compliance tasks (GDPR, AI Act, etc.).
Analysis of LLM usage in legal and compliance tasks reveals that models often produce confident but unverifiable citations, raising questions about reliable legal grounding for AI outputs.
When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination
This paper investigates how LLMs degrade in detecting planted document contaminants as batch size increases, leading to confident hallucinations of non-existent errors, and recommends bounded batch sizes and verification mechanisms for reliable auditing.
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
This paper presents a mechanistic analysis of why LLMs hallucinate when reasoning over linearized structured knowledge, finding that hallucinations stem from systematic internal dynamics such as attention on shortcut cues and failures in semantic grounding in feed-forward layers, rather than random noise.