ActInf GuestStream 084.1 ~ Anthropocentric bias and the possibility of artificial cognition

Raphael Milliere, Charles Rathkopf
"Anthropocentric bias and the possibility of artificial cognition"
https://arxiv.org/abs/2407.03859

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.

arXiv:2407.03859

Active Inference Institute information:
Website: https://activeinference.org/
Twitter: https://twitter.com/InferenceActive
Discord: https://discord.gg/8VNKNp4jtx
YouTube: https://www.youtube.com/c/ActiveInference/
Active Inference Livestreams: https://coda.io/@active-inference-institute/livestreams