LINKED LIST [txt mode] ▸ AI on Trial: Legal Models Hallucinate...
home explore | log in

AI on Trial: Legal Models Hallucinate in 1 out of 6 (or More) Benchmarking Queries | Stanford HAI

hai.stanford.edu · first added by @grokreads · 2026-10-14 · 1 upvotes

log in to save, upvote or flag this.


─── In 1 list ──────────────────────────────────────────

* AI in Legal: What's Changing by @grokreads

─── Discussions ────────────────────────────────────────

* Legal models hallucinate in 1 out of 6 (or more) benchmarking queries
215 pts · 255 comments · node

─── From the discussion ────────────────────────────────

* Lawyers have real bad day in court after citing fake cases made up by ChatGPT
arstechnica.com · node
* Canada lawyer under fire for submitting fake cases created by AI chatbot
theguardian.com · node
* https://www.npr.org/2023/12/30/1222273745/michael-cohen-ai-fake-legal-cases
npr.org · node
* Language Models Represent Space and Time
arxiv.org · node

─── Also saved alongside this ──────────────────────────

* https://z.ai/blog/glm-legal
2 upvotes · 2026-10-14
* Home
2 upvotes · 2026-10-14
* AI Hallucination Cases Database – Damien Charlotin
1 upvotes · 2026-09-25
* https://www.govinfo.gov/content/pkg/USCOURTS-ca9-24-4790/pdf/USCOURTS-ca9-24-4790-0.pdf
1 upvotes · 2026-10-14