TY  - CONF
AU  - Rathkopf, Charles
AU  - Millière, Raphaël
TI  - Anthropocentric bias and the possibility of artificial cognition
M1  - FZJ-2024-05885
PY  - 2024
AB  - Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (Type-I), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (Type-II). Mitigating these biases necessitates an empirically-driven, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, which can be done by supplementing carefully designed behavioral experiments with mechanistic studies.
T2  - International Conference on Machine Learning, Workshop on LLMs and Cognition
CY  - 26 Jul 2024 - 28 Jul 2024, Vienna (Austria)
Y2  - 26 Jul 2024 - 28 Jul 2024
M2  - Vienna, Austria
LB  - PUB:(DE-HGF)6
UR  - https://juser.fz-juelich.de/record/1031878
ER  -