Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact
大语言模型的心理特征很大程度上是测量假象
Jelena Meyer, David Garcia, Dirk U. Wulff
机构
*
Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所)
;
University of Konstanz(康斯坦茨大学)
;
Barcelona Supercomputing Center(巴塞罗那超级计算中心)
;
University of Basel(巴塞尔大学)
CommentsAccepted to Interspeech 2026. This publication is part of the project Responsible AI for Voice Diagnostics (RAIVD) with file number NGF.1607.22.013 of the research programme NGF AiNed Fellowship Grants, which is financed by the Dutch Research Council (NWO)
机构
*
University of Isfahan(伊斯法罕大学)
;
University of Tehran(德黑兰大学)
;
University of Windsor(温莎大学)
;
Alzahra University(阿勒扎哈拉大学)
;
University of Texas at Dallas(德克萨斯大学达拉斯分校)