Kedis ku xidhan hagaha · Adag Heerka

Heerarka dhalanteedka ee Kediska Qalabka AI ee Sharci

Wuxuu tijaabiyaa sida daraasadaha Stanford ay u qeexeen oo ay u cabbireen aragtiyaha AI ee sharciga ah, maxay jawaabaha khaldan yihiin, iyo sababta dib-u-soo-celinta-jiilka la kordhiyey uu weli u guuldareysto.

Wadooyinka haga ee la xidhiidhaHeerarka dhalanteedka ee Aaladaha AI ee sharciga ah
Su'aal 1 ee 8

Sidee buu Stanford u noqday "Hallucination-free?" daraasaddu waxay qeexdaa dhalanteed?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Sidee buu Stanford u noqday "Hallucination-free?" daraasaddu waxay qeexdaa dhalanteed?
    • Any answer longer than the source document
    • An answer that is either incorrect or misgrounded
    • Only a citation to a case that does not exist
    • Any answer the tool took more than a minute to produce
  2. Marka la eego shuruudaha daraasadda Stanford, waa maxay jawaabta 'qaldan'?
    • An answer that refuses to respond
    • An answer written in the wrong language
    • An answer with no citations at all
    • An answer that cites a real source that does not support its claim
  3. Qalabkee ayaa si fiican u sameeyay imtixaankii Stanford 2024 laakiin wali lagu sawiray in ka badan boqolkiiba 17 su'aalaha?
    • Lexis+ AI
    • Westlaw AI-Assisted Research
    • Ask Practical Law AI
    • GPT-4 used as a comparison
  4. Immisa kala duwan oo dhalanteed ah ayay "khiyaasooyinka sharciga ah ee waaweyn" ka heleen chatbots ujeedo-guud ah oo ku saabsan su'aalaha maxkamadda federaalka ee la xaqiijin karo?
    • 1 to 3 percent
    • 17 to 33 percent
    • 69 to 88 percent
    • 95 to 100 percent
  5. Maxay tahay sababta tallaabada dib u soo celinta ay u heli karto maamulka khaldan xitaa marka kaydka xogta uu ka kooban yahay mid sax ah?
    • Legal databases are encrypted and cannot be searched
    • Retrieval only works for statutes, not cases
    • Retrieval ranks documents alphabetically
    • Retrieval matches similar wording or meaning, which is not the same as legal relevance
  6. What tendency did the research find when questions contained a false premise?
    • Models tended to accept the premise and answer as if it were true
    • Models always corrected the premise
    • Models refused every such question
    • Models replied only with the text of the relevant statute
  7. Which mitigation specifically helps flag a cited case that was later reversed or overruled?
    • Raising the model's temperature setting
    • Making answers shorter
    • Translating the query into another language
    • Connecting a citator such as KeyCite or Shepard's
  8. What marketing claim did the Stanford study's title directly question?
    • That legal AI tools were cheaper than paralegals
    • That some tools were 'hallucination-free'
    • That legal AI could pass the bar exam
    • That AI tools were approved by courts