Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Haslett, David A."'
Large language models (LLMs) such as ChatGPT and Vicuna have shown remarkable capacities in comprehending and producing language. However, their internal workings remain a black box, and it is unclear whether LLMs and chatbots can develop humanlike c
Externí odkaz:
http://arxiv.org/abs/2303.08014
Autor:
Haslett, David A., Cai, Zhenguang G.
Publikováno v:
In Journal of Memory and Language October 2024 138
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
This experiment tests whether ChatGPT's production of anaphoric expressions (e.g., he/she) is sensitive to verb types (stimulus-experiencer vs. experiencer-stimulus verbs), as humans have been shown to be (e.g., Fukumura & van Gompel, 2010).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa0b2b4d28d7181ed401bc875fa62062
This experiment tests whether ChatGPT is susceptible to structural priming and the lexical boost, as humans have been shown to be (e.g., Pickering & Branigan, 1998).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::018328987ba284249c3fb0afc04e98d4
We will investigate VP-NP attachment ambiguity and test whether syntactic ambiguity resolution is influenced by contextual information in ChatGPT, as in humans (e.g., Altmann & Steedman, 1988). We also test whether ChatGPT comes up with multiple inte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40ad32e91fb4c1f2ede887eab1ddac33
How many animals of each kind did Moses take on the ark? People often fail to notice that this question incorrectly refers to Moses rather than Noah (Erickson & Mattson, 1981), a phenomenon known as semantic illusions. We will investigate whether Cha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d6062132640d4bfc536c544867158070
This experiment tests whether ChatGPT is susceptible to word meaning priming, as humans have been shown to be (e.g., Rodd et al., 2013).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbab6b3275b3f8caf772c928971e2f1a
This experiment tests whether ChatGPT can infer the gender of novel personal names based on phonology, as humans have been shown to do.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c58a78217c62668889de23957a8c536b