Enregistré dans:
Détails bibliographiques
Auteurs principaux: Roberts, Jesse, Moore, Kyle, Pham, Thao, Ewaleifoh, Oseremhen, Fisher, Doug
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.06349
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914959551627264
author Roberts, Jesse
Moore, Kyle
Pham, Thao
Ewaleifoh, Oseremhen
Fisher, Doug
author_facet Roberts, Jesse
Moore, Kyle
Pham, Thao
Ewaleifoh, Oseremhen
Fisher, Doug
contents This paper evaluates whether large language models (LLMs) exhibit cognitive fan effects, similar to those discovered by Anderson in humans, after being pre-trained on human textual data. We conduct two sets of in-context recall experiments designed to elicit fan effects. Consistent with human results, we find that LLM recall uncertainty, measured via token probability, is influenced by the fan effect. Our results show that removing uncertainty disrupts the observed effect. The experiments suggest the fan effect is consistent whether the fan value is induced in-context or in the pre-training data. Finally, these findings provide in-silico evidence that fan effects and typicality are expressions of the same phenomena.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06349
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Model Recall Uncertainty is Modulated by the Fan Effect
Roberts, Jesse
Moore, Kyle
Pham, Thao
Ewaleifoh, Oseremhen
Fisher, Doug
Computation and Language
Artificial Intelligence
This paper evaluates whether large language models (LLMs) exhibit cognitive fan effects, similar to those discovered by Anderson in humans, after being pre-trained on human textual data. We conduct two sets of in-context recall experiments designed to elicit fan effects. Consistent with human results, we find that LLM recall uncertainty, measured via token probability, is influenced by the fan effect. Our results show that removing uncertainty disrupts the observed effect. The experiments suggest the fan effect is consistent whether the fan value is induced in-context or in the pre-training data. Finally, these findings provide in-silico evidence that fan effects and typicality are expressions of the same phenomena.
title Large Language Model Recall Uncertainty is Modulated by the Fan Effect
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.06349