kaal:claim:5541658-007

Retrieval-augmented generation reduces but does not eliminate hallucination: leading legal research tools including Lexis+AI and Westlaw AI-Assisted Research still generate false citations or facts in 17 to 33 percent of cases.

A later claim in the corpus revises this one. Prefer quoting kaal:claim:6421319-022.

Source quote, verbatim

the risk of "hallucinations," where AI generates false legal citations or facts, as observed in tools like Lexis+AI and Westlaw AI-Assisted Research, which hallucinate in 17–33% of cases.

From

Wulf A. Kaal, Morgan A. Gray, The Evolving Role of Artificial Intelligence in Law (2025), Transparency and Interpretability, p. 22
https://ssrn.com/abstract=5541658 · source PDF

Cite as

Wulf A. Kaal, Morgan A. Gray, The Evolving Role of Artificial Intelligence in Law (2025). SSRN: https://ssrn.com/abstract=5541658

Holds when

RAG-based commercial legal research platforms
as measured at the time of the cited study; the authors note rates are progressively improving

Classification

failuresupport: evidencedfailure: residual hallucination under RAGfamily: ai-model-and-training-failurelaw-and-legal-systems

Verify

The quote above is an exact substring of the source PDF, whose sha256 is e543a2d698fcd522d4d02e034cc9ee1344d0015d2c824b40b9e05ab7c0728c60. Extraction method: pdf-text-layer.
Attestation record: colloquium/attestations/6313a9fb5d4fded9...json
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/5541658-007.md | sha256sum