Frontier LLMs produce fully compliant legal citations only 42.6% of the time, new benchmark finds
hoofnagle · x · 2026-08-21
A new benchmark of 2,058 Bluebook (US legal citation format) queries shows that, on average, frontier language models produce a fully compliant legal citation only 42.6% of the time in a zero-shot setting — a "disappointing but important" result highlighting that LLMs remain unreliable for professional legal drafting.
More from Models
- Pangram v4 Model Claims to Remove AI Watermarks and Mimic Human Writing — Scobleizer · 2026-08-21
- Brundage: something funky going on with ChatGPT inference, likely testing — Miles_Brundage · 2026-08-21
- Does Claude perform better in 'claudish'? Researchers call for empirical measures — voooooogel · 2026-08-21
- What's left for hobbyists to post-train on in 2026? One bets on self-play poker — No-Compote-6794 · 2026-08-21
- Google event demos Gemini 3.7 Flash and new AI Studio features — jocarrasqueira · 2026-08-21
- User complains Claude has become 'lobotomized' — what happened? — tech__unicorn · 2026-08-21