Il prossimoAvanti in Fondamenti di intelligenza artificiale
Miti dell'intelligenza artificiale
Società
GUIDA ALL'AI linguistica
An AI hallucination is generated content that presents erroneous or unsupported information as if it were reliable.
Ascolta questa guidaNarrato dall'IA · ~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.
Newsletter gratuita
Tre storie verificate sull'IA ogni mattina nei giorni feriali, scritte in un inglese semplice. Gratuito per sempre, senza pubblicità.
Un'email ogni giorno feriale. Disiscriviti con un clic. Non vendiamo né condividiamo mai il tuo indirizzo.
Mettiti alla prova
Feedback immediato su ogni risposta e un certificato condivisibile con un ID verificabile una volta superato un corso.
Sostieni l'istruzione gratuita sull'IA. AI Understanding è un'organizzazione non profit 501(c)(3) — nessun annuncio, nessun paywall, mai. Fai una donazione
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.
L'obiettivo formativo riguarda il testo previsto; la verifica dei fatti necessita di prove a sostegno.
Poiché l'output falso è fluido e sicuro, si fonde con le risposte corrette ed è facile per gli utenti fidarsi.
RAG riduce le allucinazioni fondando le risposte su fonti reali, ma i modelli possono comunque avere allucinazioni quando il recupero è imperfetto o è in conflitto con la loro conoscenza interna.
Inventare una citazione inesistente ma dall’aspetto realistico è una classica allucinazione: sicura, specifica e falsa.
La messa a terra può aiutare, mentre l'esistenza e il supporto delle rivendicazioni necessitano ancora di verifica.
Continua a imparare
Altre guide selezionate per questo argomento
Il prossimoAvanti in Fondamenti di intelligenza artificiale
Miti dell'intelligenza artificiale
Società