The Debate Over Understanding in AI's Large Language Models
A preprint by Melanie Mitchell and David C. Krakauer, arXiv preprint 2210.13966, dated 14 October 2022. arXiv v1, 14 October 2022; the PNAS version appeared in March 2023.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Melanie Mitchell and David C. Krakauer.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2022-10-14.
- Exact source
- The Debate Over Understanding in AI's Large Language Models arXiv preprint 2210.13966; published in PNAS 120(13), 2023 · published 2022-10-14 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 0974d050bf846a03009b130279aa5d40b322a6aee30d1c7e6e4eea3dfd280f8d). arXiv v1 of 14 October 2022.
Appears in
- Arguments about catastrophic risk from advanced AI →1 record on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Bears on · 1
Propositions a passage comes close to without meeting the criterion; each record names what is missing.
- Language models lack agency or understandingMitchell and Krakauer's paper of October 2022 states that abilities such as learning from few examples, robust reasoning and explaining one's reasoning are lacking in current LLMs, and that current sciences of intelligence are inadequate to settle whether LLMs understand.2022-10-14 · publication · Stated in source · Supported Inspect claim & evidence ↗Language models lack agency or understanding: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.