State vs. Trait Anxiety in Causal Language Models

Karin Shistik, Idan-Chaim Cohen, Aviad Elyashar, Ortal Slobodin, Odeya Cohen, Rami Puzis


Abstract
Psychological constructs in humans range along a state–trait continuum: traits persist across situations, while states fluctuate with context. Studies have shown that language models exhibit measurable psychological constructs, yet whether these constructs differ in contextual stability, as the state–trait distinction predicts, remains untested. We present the Questionnaire for Causal Language Models (QCLM), a psychometric framework that measures constructs through next-token probability distributions of base models. Applying QCLM to 35 causal language models under vanilla, stress, and neutral conditions, we assess two anxiety instruments targeting opposite ends of the state–trait continuum: STAI-S (state anxiety) and STAI-T (trait anxiety). Paired effect sizes and variance decomposition reveal that state anxiety is more sensitive to stress manipulation than trait anxiety: stimulus type accounts for a larger share of variance in state anxiety, while model identity contributes more to trait anxiety. These results provide empirical evidence that the state–trait distinction extends to language model behavior.
Anthology ID:
2026.socon-1.1
Volume:
Proceedings of the 1st Workshop on Social Context (SoCon) and the 2nd Workshop on Integrating NLP and Psychology to Study Social Interactions (NLPSI) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Marco Antonio Stranisci, Neele Falk, Sofie Labat, Soda Marem Lo, Aswathy Velutharambath, Sabine Weber, Rossana Damiano, Simona Frenda, Veronique Hoste, Bennett Kleinberg, Roman Klinger, Viviana Patti, Flor Miriam Plaza-del-Arco, Maarten Sap, Seid Muhie Yimam
Venues:
SoCon | NLPSI | WS
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
1–14
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-soconnlpsi-01
DOI:
10.63317/4q2w8y6y32fu
Bibkey:
Cite (ACL):
Karin Shistik, Idan-Chaim Cohen, Aviad Elyashar, Ortal Slobodin, Odeya Cohen, and Rami Puzis. 2026. State vs. Trait Anxiety in Causal Language Models. In Proceedings of the 1st Workshop on Social Context (SoCon) and the 2nd Workshop on Integrating NLP and Psychology to Study Social Interactions (NLPSI) @ LREC 2026, pages 1–14, Palma, Mallorca (Spain). European Language Resources Association (ELRA).
Cite (Informal):
State vs. Trait Anxiety in Causal Language Models (Shistik et al., SoCon-NLPSI 2026)
Copy Citation: