Embers of autoregression show how large language models are shaped by the problem they are trained to solve.
Saved in:
| Title: | Embers of autoregression show how large language models are shaped by the problem they are trained to solve. |
|---|---|
| Authors: | McCoy RT; Department of Computer Science, Princeton University, Princeton, NJ 08542., Yao S; Department of Computer Science, Princeton University, Princeton, NJ 08542., Friedman D; Department of Computer Science, Princeton University, Princeton, NJ 08542., Hardy MD; Department of Psychology, Princeton University, Princeton, NJ 08542., Griffiths TL; Department of Computer Science, Princeton University, Princeton, NJ 08542.; Department of Psychology, Princeton University, Princeton, NJ 08542. |
| Source: | Proceedings of the National Academy of Sciences of the United States of America [Proc Natl Acad Sci U S A] 2024 Oct 08; Vol. 121 (41), pp. e2322420121. Date of Electronic Publication: 2024 Oct 04. |
| Publication Type: | Journal Article |
| Journal Info: | Publisher: National Academy of Sciences Country of Publication: United States NLM ID: 7505876 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1091-6490 (Electronic) Linking ISSN: 00278424 NLM ISO Abbreviation: Proc Natl Acad Sci U S A Subsets: MEDLINE |
| Database: | MEDLINE Ultimate |
| ISSN: | 1091-6490 |
|---|---|
| DOI: | 10.1073/pnas.2322420121 |
