Mai departeUrmătorul în Fundamentele AI
Mituri AI
Societate
GHID AI limbaj
An AI hallucination is generated content that presents erroneous or unsupported information as if it were reliable.
Ascultă acest ghidNarativ AI · ~3 min
Fluent wording can conceal invented references, incorrect quantities, or contradictions of supplied evidence, making verification necessary.
Generated answers can contain false statements even when their wording is clear and confident. NIST's Generative AI Profile discusses this risk as confabulation, including erroneous content and outputs that contradict their inputs. A next-token prediction objective does not itself constitute a factual verification process. Models can produce plausible continuations without adequate evidence for a specific name, number, or reference. This is one reason to examine the content rather than infer reliability from style. It is also incorrect to assume that a model never acknowledges uncertainty: some systems can abstain or qualify responses, although such behavior is not a guarantee of accuracy. Retrieval-augmented generation adds information from retrieved material, but the model may still use it incorrectly or generate unsupported details. Verification therefore has two parts. Check whether the cited source exists, then check whether it supports the particular claim. A real URL can lead to a genuine page that says something different. For a supplied document, compare relevant details directly. In an illustrative example, the document says delivery takes five business days, while a summary says two; that discrepancy is a source-faithfulness error even if the summary reads naturally. Long answers may mix supported and unsupported claims. FActScore studies evaluation of fine-grained factual statements against a knowledge source, illustrating why an answer-wide impression can miss individual errors. Evaluation and mitigation should use defined tasks and evidence rather than treating confidence, citations, or a product announcement as proof of universal reliability.
Checking whether a cited paper exists and actually supports the associated claim.
Comparing quantities in a generated summary with the supplied document.
Inspecting a proposed API name against the relevant library documentation.
Evaluating factual claims individually rather than rating an answer by fluency alone.
Research can improve grounding, uncertainty communication, abstention, and factual evaluation. Claims about progress should state the model, task, evidence, and measurement conditions. Neither a narrow benchmark result nor a statement that hallucinations are eliminated establishes reliability on every application. Continued evaluation should include representative errors and changes in source availability. For consequential uses, the workflow needs evidence checks appropriate to the claim and a way to resolve uncertain or contradictory outputs before relying on them.
Buletin gratuit
Trei povești AI verificate în fiecare dimineață de zi lucrătoare, scrise în engleză simplă. Gratuit pentru totdeauna, fără reclame.
Un e-mail în fiecare zi lucrătoare. Dezabonare cu un singur clic. Nu vindem niciodată și nu împărtășim adresa ta.
Testează-te
Feedback instantaneu la fiecare răspuns și un certificat partajabil cu un ID verificabil după ce parcurgi un curs.
Susține educația AI gratuită. AI Understanding este o organizație nonprofit 501(c)(3) — fără reclame, fără barieră de plată, pentru totdeauna. Fă o donație
An AI hallucination is generated content that presents erroneous or unsupported information as if it were reliable. Fluent wording can conceal invented references, incorrect quantities, or contradictions of supplied evidence, making verification necessary.
The training objective concerns predicted text; factual verification needs supporting evidence.
Deoarece rezultatul fals este fluent și încrezător, se îmbină cu răspunsurile corecte și este ușor de încredere pentru utilizatori.
RAG reduce halucinațiile prin fundamentarea răspunsurilor în surse reale, dar modelele pot încă halucina atunci când recuperarea este imperfectă sau intră în conflict cu cunoștințele lor interne.
A inventa o citare inexistentă, dar cu aspect realist, este o halucinație clasică - încrezătoare, specifică și falsă.
Grounding can help, while existence and claim support still need verification.
Continuați să învățați
Mai multe ghiduri alese pentru acest subiect
Mai departeUrmătorul în Fundamentele AI
Mituri AI
Societate