Testing Stimulus Equivalence in Transformer-Based Agents

Alexis Carrillo and Moisés Betancort ()
Additional contact information
Alexis Carrillo: Departamento de Psicología Clínica, Psicobiología y Metodología, Campus de Guajara, Universidad de La Laguna, Apartado 456, 38200 San Cristóbal de La Laguna, Spain
Moisés Betancort: Departamento de Psicología Clínica, Psicobiología y Metodología, Campus de Guajara, Universidad de La Laguna, Apartado 456, 38200 San Cristóbal de La Laguna, Spain

Future Internet, 2024, vol. 16, issue 8, 1-24

Abstract: This study investigates the ability of transformer-based models (TBMs) to form stimulus equivalence (SE) classes. We employ BERT and GPT as TBM agents in SE tasks, evaluating their performance across training structures (linear series, one-to-many and many-to-one) and relation types (select–reject, select-only). Our findings demonstrate that both models performed above mastery criterion in the baseline phase across all simulations ( n = 12). However, they exhibit limited success in reflexivity, transitivity, and symmetry tests. Notably, both models achieved success only in the linear series structure with select–reject relations, failing in one-to-many and many-to-one structures, and all select-only conditions. These results suggest that TBM may be forming decision rules based on learned discriminations and reject relations, rather than responding according to equivalence class formation. The absence of reject relations appears to influence their responses and the occurrence of hallucinations. This research highlights the potential of SE simulations for: (a) comparative analysis of learning mechanisms, (b) explainability techniques for TBM decision-making, and (c) TBM bench-marking independent of pre-training or fine-tuning. Future investigations can explore upscaling simulations and utilize SE tasks within a reinforcement learning framework.

Keywords: stimulus equivalence; transformers; BERT; GPT; matching to sample; reject control; training structures (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/8/289/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/8/289/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:8:p:289-:d:1452956

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().