- Main
Do Models Capture Individuals?Evaluating Parameterized Models for Syllogistic Reasoning
Abstract
The prevailing focus on aggregated data and the lacking group-to-individual generalizability it entails have recently been iden-tified as a major cause for the low performance of cognitivemodels in the field of syllogistic reasoning research. This arti-cle attempts to add to the discussion about the performance ofcurrent syllogistic reasoning models by considering the param-eterization capabilities some cognitive models offer. To thisend, we propose a model evaluation setting targeted specifi-cally toward analyzing the capabilities of a model to fine-tuneits inferential mechanisms to individual human reasoning data.This allows us to (1) quantify the degree to which models areable to capture individual human reasoning behavior, (2) ana-lyze the efficiency of the parameters used by models, and (3)examine the functional differences between the prediction ca-pabilities of competing models on a more detailed level. Weapply this method to two state-of-the-art models for syllogisticreasoning, mReasoner and the Probability Heuristics Model,analyze the obtained results and discuss their implication withrespect to the general field of cognitive modeling.
Main Content
Enter the password to open this PDF file:
-
-
-
-
-
-
-
-
-
-
-
-
-
-