InayofuataMwongozo unaofuata
Vyombo vya Kuandika vya AI
Lugha AI
Lugha AI MWONGOZO
Hallucination Rates in Legal AI Tools
Independent testing has found that AI legal research tools built on retrieval-augmented generation (RAG) still give incorrect or unsupported answers a meaningful share of the time.
Katika ukurasa huu4 dakika kusoma
Muhtasari
A 2024 Stanford study found hallucinations in more than one in six queries even for the best-performing commercial tool. It matters because vendors marketed these tools as avoiding hallucinations, and lawyers who rely on them are still responsible for every citation they file.
Dive ya kina
Two Stanford-affiliated studies shaped the debate. The first, "Large Legal Fictions" (2024), by Matthew Dahl, Varun Magesh, Mirac Suzgun and Daniel Ho, tested general-purpose chatbots on verifiable questions about federal court cases. It found hallucination rates between 69 and 88 percent on those questions. Models also tended to accept false premises built into the questions. Commercial legal vendors argued that their tools avoided this problem through retrieval-augmented generation, which grounds answers in real legal databases. Some marketing used phrases such as "hallucination-free." In 2024, researchers at Stanford's RegLab and Institute for Human-Centered AI tested that claim in a study titled "Hallucination-Free?" They ran more than 200 legal queries through Lexis+ AI, Westlaw AI-Assisted Research and Ask Practical Law AI, with GPT-4 as a comparison. They counted an answer as a hallucination if it was either incorrect or misgrounded. Misgrounded means it cited a real source that does not support the claim. Lexis+ AI performed best, yet still hallucinated on more than 17 percent of queries. Westlaw's tool hallucinated on roughly a third. Ask Practical Law AI often gave incomplete answers. An early version of the paper was criticized because the researchers first lacked access to Westlaw's research tool; they later tested it and revised the paper. Retrieval reduces errors but does not remove them, for several reasons. The retriever may find documents that share words with the query but are not legally relevant. It may miss the controlling authority, or pull a case from the wrong jurisdiction or a superseded version of a rule. The model may then misread or ignore what was retrieved, blend sources together, or go along with a false premise. A common misconception is that a correct-looking citation means a correct answer. The misgrounded category shows that a real citation can support a false claim.
Athari za kimkakati
Kasi na kiwango
Mitiririko ya kazi ya lugha inaweza kusonga kwa kasi zaidi bila kuacha uthabiti.
Kufikia na kufikia
Inapanua ufikiaji katika lugha na mitindo ya mawasiliano.
Maamuzi ya wazi zaidi
Timu zinaweza kutumia muda mwingi kufanya uamuzi huku otomatiki ikishughulikia marudio.
The Future of Hallucination Rates in Legal AI Tools
Vendors have updated their products since the 2024 studies, so specific error rates may not describe current versions. That is why repeated independent testing matters more than any single number. Benchmarking efforts by third parties and by law firms themselves are becoming more common. Better citators, agent-style workflows that check their own citations, and stronger grounding may reduce errors. Nothing so far shows that retrieval will remove them entirely. Courts continue to see filings with fabricated or misrepresented authority, and some have imposed sanctions. For the foreseeable future, human review of every cited authority remains a professional obligation, whatever a vendor claims.
Utekelezaji wa Ulimwengu Halisi
An associate asks a research tool why a court ruled a certain way in a case that actually went the other way. The tool accepts the false premise and explains the invented ruling, citing a real opinion.
A tool returns a real appellate case with an accurate citation for a proposition the case never addresses. This is a 'misgrounded' answer that looks trustworthy until someone reads the opinion.
A research tool cites a decision that was later reversed, because it retrieved the older opinion and did not check its later history.
A legal department tests two vendors on its own set of 100 questions with known answers. It records whether each citation exists, whether it supports the claim, and whether the answer is complete.
Hatari & Walinzi
Mambo ya ukweli yanaweza kuingiza ripoti kwa utulivu, mitiririko ya usaidizi, au matokeo ya utafiti.
Usikivu wa haraka unaweza kuunda matokeo yasiyolingana katika maombi sawa.
Data nyeti ya maandishi inaweza kufichuliwa ikiwa vidhibiti vya ufikiaji ni dhaifu.
Ramani ya Utekelezaji
Bainisha umbizo la towe, toni na viwango vya ubora kabla ya kusambaza.
Majibu ya msingi na vyanzo vinavyoaminika wakati wowote usahihi ni muhimu.
Weka ukaguzi wa ukaguzi wa kibinadamu kwa matokeo ya juu.
Fuatilia mifumo ya kushindwa na fundisha tena vidokezo au mtiririko wa kazi mara kwa mara.
Endelea Kuchunguza
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Hallucination Rates in Legal AI Tools quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Maswali yanayoulizwa mara kwa mara
What is Hallucination Rates in Legal AI Tools?
Independent testing has found that AI legal research tools built on retrieval-augmented generation (RAG) still give incorrect or unsupported answers a meaningful share of the time. A 2024 Stanford study found hallucinations in more than one in six queries even for the best-performing commercial tool. It matters because vendors marketed these tools as avoiding hallucinations, and lawyers who rely on them are still responsible for every citation they file.
Jinsi gani Stanford "Hallucination-Free?" utafiti kufafanua hallucination?
Utafiti ulihesabu aina mbili za makosa: taarifa ambazo si sahihi, na taarifa zinazoungwa mkono na nukuu ambayo haiungi mkono.
Kwa masharti ya utafiti wa Stanford, jibu 'lililopotoshwa' ni nini?
Jibu lisilo na msingi linaonyesha mamlaka ya kweli, lakini mamlaka hiyo haiungi mkono kile ambacho jibu linasema. Hii inafanya ionekane ya kuaminika zaidi kuliko ilivyo.
Ni zana gani iliyofanya vizuri zaidi katika jaribio la Stanford la 2024 lakini bado ilishawishiwa kwa zaidi ya asilimia 17 ya maswali?
Lexis+ AI ilikuwa na matokeo bora zaidi, lakini bado ilishawishiwa kwa zaidi ya asilimia 17 ya maswali. Zana ya Westlaw ilionekana katika takriban theluthi moja.
Je, "Hadithi Kubwa za Kisheria" ilipata masafa gani ya mazungumzo ya madhumuni ya jumla kuhusu maswali ya mahakama ya shirikisho yanayoweza kuthibitishwa?
Utafiti uligundua kuwa chatbots za jumla zilivutia kati ya asilimia 69 na 88 ya muda kwenye maswali haya mahususi, yanayoweza kuthibitishwa.
Kwa nini hatua ya kurejesha inaweza kupata mamlaka isiyo sahihi hata wakati hifadhidata ina ile inayofaa?
Virejeshi vinapata ukaribu katika maneno au maana. Upinzani, muhtasari wa hoja ya upande mwingine, au kesi kutoka kwa mamlaka isiyo sahihi inaweza kuwa na cheo cha juu bila kuwa na mamlaka inayodhibiti.
Endelea kujifunza
Miongozo inayohusiana
Miongozo zaidi imechaguliwa kwa mada hii