001031878 001__ 1031878
001031878 005__ 20241021205501.0
001031878 037__ $$aFZJ-2024-05885
001031878 1001_ $$0P:(DE-Juel1)176538$$aRathkopf, Charles$$b0$$eCorresponding author$$ufzj
001031878 1112_ $$aInternational Conference on Machine Learning, Workshop on LLMs and Cognition$$cVienna$$d2024-07-26 - 2024-07-28$$wAustria
001031878 245__ $$aAnthropocentric bias and the possibility of artificial cognition
001031878 260__ $$c2024
001031878 3367_ $$033$$2EndNote$$aConference Paper
001031878 3367_ $$2DataCite$$aOther
001031878 3367_ $$2BibTeX$$aINPROCEEDINGS
001031878 3367_ $$2DRIVER$$aconferenceObject
001031878 3367_ $$2ORCID$$aLECTURE_SPEECH
001031878 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1729513812_3409$$xInvited
001031878 520__ $$aEvaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (Type-I), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (Type-II). Mitigating these biases necessitates an empirically-driven, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, which can be done by supplementing carefully designed behavioral experiments with mechanistic studies.
001031878 536__ $$0G:(DE-HGF)POF4-5255$$a5255 - Neuroethics and Ethics of Information (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001031878 7001_ $$0P:(DE-HGF)0$$aMillière, Raphaël$$b1
001031878 909CO $$ooai:juser.fz-juelich.de:1031878$$pVDB
001031878 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176538$$aForschungszentrum Jülich$$b0$$kFZJ
001031878 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5255$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001031878 9141_ $$y2024
001031878 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001031878 980__ $$aconf
001031878 980__ $$aVDB
001031878 980__ $$aI:(DE-Juel1)INM-7-20090406
001031878 980__ $$aUNRESTRICTED