A mechanistic interpretability perspective on personality in large language models.

Yuhao Dan|Lang Yu|Jiaju Lin|Qin Chen|Jie Zhou|Junfeng Tian|Qingchun Bai|Liang He


Anthology ID:DBLP:journals/ipm/DanYLCZTBH26
Year:2026
Venue:Information Processing and Management
Pages:104962
URL:https://doi.org/10.1016/J.IPM.2026.104962
DOI:https://doi.org/10.1016/J.IPM.2026.104962
DBLP:journals/ipm/DanYLCZTBH26
BibTeX:
@article{dan-2026-mechanistic, author = {Yuhao Dan and Lang Yu and Jiaju Lin and Qin Chen and Jie Zhou and Junfeng Tian and Qingchun Bai and Liang He}, title = {{A mechanistic interpretability perspective on personality in large language models}}, journal = {Information Processing and Management}, volume = {63}, number = {8}, pages = {104962}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2026.104962}, doi = {https://doi.org/10.1016/J.IPM.2026.104962} }