Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Why Question Order Matters: A Requirement-First Interpretation of the QQ Equality

Song-Ju Kim

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.2139/ssrn.7078790

Related papers

Psychological Effects and QQ-equality

Andrei Yu. Khrennikov

Springer eBooks•Jan 1, 2023•0 citations

Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism Characterization and a Saturation Caveat

Pilsung Kang

Question-order effects in human survey data have been reported to approximately satisfy the QQ (quantum question) equality, a parameter-free prediction of the standard projective quantum question-order model. We develop this equality into an audit framework for sequential binary judgments of autoregressive large language models (LLMs). Theoretically, we characterize mechanism families that satisfy QQ robustly, show that classical repetition can reproduce the equality exactly, and combine QQ with the rank-2 Contextuality-by-Default criterion through $|q_{QQ}| \le \mathrm{OSS}$. This separates order sensitivity, QQ imbalance, and residual contextuality rather than treating them as interchangeable signatures. Methodologically, we introduce a committed multi-turn forced-branch protocol that reconstructs order-conditioned joint distributions from next-token log-probabilities under counterbalanced label mappings and pre-specified health gates. A first-signal pilot on an open-weight instruction-tuned model reveals the central measurement problem. Although all pre-specified health gates passed, the binary-conditioned distributions were near-deterministic for 17 of 18 item pairs under the direct-evaluation framing and 7 of 8 under the persona framing. Label assignment materially changed several mapping-specific QQ verdicts, and no item was certified as residually contextual. Thus, under the tested conditions, the observed QQ outcomes did not uniquely identify a response mechanism in the presence of a saturated and label-sensitive measurement interface. The main implication is methodological: next-token probabilities should not be interpreted as survey-response distributions without first establishing adequate dispersion. We therefore argue that saturation screening and label counterbalancing should precede structural interpretation in distribution-level audits of LLM judgments.

cs.CLCross-listedarXiv:2607.17219•Jul 21, 2026•0 citations

Question Order and Response Replicability Effects

Andrei Yu. Khrennikov

Springer eBooks•Jan 1, 2023•0 citations

A Quantum Question Order Model Supported by Empirical Tests of anA Prioriand Precise Prediction

Zheng Wang, Jerome R. Busemeyer

Question order effects are commonly observed in self-report measures of judgment and attitude. This article develops a quantum question order model (the QQ model) to account for four types of question order effects observed in literature. First, the postulates of the QQ model are presented. Second, an a priori, parameter-free, and precise prediction, called the QQ equality, is derived from these mathematical principles, and six empirical data sets are used to test the prediction. Third, a new index is derived from the model to measure similarity between questions. Fourth, we show that in contrast to the QQ model, Bayesian and Markov models do not generally satisfy the QQ equality and thus cannot account for the reported empirical data that support this equality. Finally, we describe the conditions under which order effects are predicted to occur, and we review a broader range of findings that are encompassed by these very same quantum principles. We conclude that quantum probability theory, initially invented to explain order effects on measurements in physics, appears to be a powerful natural explanation for order effects of self-report measures in social and behavioral sciences, too.

Topics in Cognitive Science•Sep 11, 2013•235 citations

Explaining and Predicting Question Order Effects Using a Quantum Probability Model

Zheng Joyce Wang, Jerome R. Busemeyer

•May 25, 2011•2 citations

Kvantno probabilističko modeliranje u kognitivnoj psihologiji: efekt redoslijeda

Monika Švogor

The order effect is a well-known phenomenon in cognitive psychology which violates specific axioms of the classical probability theory and refers to different probabilities of measurement outcomes (answers to questions) depending on their order. In this research, the order effect was analyzed using quantum probabilistic modeling of cognitive processes. The Quantum Question (QQ) model suggested by Wang and Busemeyer (2013) was tested on a sample of participants that had answered three yes/no questions about a painting, in different orders. For that purpose, three problems were considered. The first problem was to examine the presence of the order effect in participants’ answers and the results showed order effects for all three questions. The second problem was to test data fitness with a model prediction called QQ equality and the data proved to be a good fit to the model. The purpose of the third problem was to examine the dependency of the q value derived from the model on a third question. Given that the QQ equality is a prediction which includes only two yes/no questions, an additional prediction was derived from the model which includes a third question and according to which, the q value is independent of a third question. The results showed a limitation in the model in explaining empirical data. A proposal was made how to expand the theory, so it would include models with three or more questions.

•Sep 18, 2018•0 citations
Question-order effects in human survey data have been reported to approximately satisfy the QQ (quantum question) equality, a parameter-free prediction of the standard projective quantum question-order model. We develop this equality into an audit framework for sequential binary judgments of autoregressive large language models (LLMs). Theoretically, we characterize mechanism families that satisfy QQ robustly, show that classical repetition can reproduce the equality exactly, and combine QQ with the rank-2 Contextuality-by-Default criterion through ∣qQQ∣≤OSS|q_{QQ}| \le \mathrm{OSS}∣qQQ​∣≤OSS. This separates order sensitivity, QQ imbalance, and residual contextuality rather than treating them as interchangeable signatures. Methodologically, we introduce a committed multi-turn forced-branch protocol that reconstructs order-conditioned joint distributions from next-token log-probabilities under counterbalanced label mappings and pre-specified health gates. A first-signal pilot on an open-weight instruction-tuned model reveals the central measurement problem. Although all pre-specified health gates passed, the binary-conditioned distributions were near-deterministic for 17 of 18 item pairs under the direct-evaluation framing and 7 of 8 under the persona framing. Label assignment materially changed several mapping-specific QQ verdicts, and no item was certified as residually contextual. Thus, under the tested conditions, the observed QQ outcomes did not uniquely identify a response mechanism in the presence of a saturated and label-sensitive measurement interface. The main implication is methodological: next-token probabilities should not be interpreted as survey-response distributions without first establishing adequate dispersion. We therefore argue that saturation screening and label counterbalancing should precede structural interpretation in distribution-level audits of LLM judgments.
Question order effects are commonly observed in self-report measures of judgment and attitude. This article develops a quantum question order model (the QQ model) to account for four types of question order effects observed in literature. First, the postulates of the QQ model are presented. Second, an a priori, parameter-free, and precise prediction, called the QQ equality, is derived from these mathematical principles, and six empirical data sets are used to test the prediction. Third, a new index is derived from the model to measure similarity between questions. Fourth, we show that in contrast to the QQ model, Bayesian and Markov models do not generally satisfy the QQ equality and thus cannot account for the reported empirical data that support this equality. Finally, we describe the conditions under which order effects are predicted to occur, and we review a broader range of findings that are encompassed by these very same quantum principles. We conclude that quantum probability theory, initially invented to explain order effects on measurements in physics, appears to be a powerful natural explanation for order effects of self-report measures in social and behavioral sciences, too.
The order effect is a well-known phenomenon in cognitive psychology which violates specific axioms of the classical probability theory and refers to different probabilities of measurement outcomes (answers to questions) depending on their order. In this research, the order effect was analyzed using quantum probabilistic modeling of cognitive processes. The Quantum Question (QQ) model suggested by Wang and Busemeyer (2013) was tested on a sample of participants that had answered three yes/no questions about a painting, in different orders. For that purpose, three problems were considered. The first problem was to examine the presence of the order effect in participants’ answers and the results showed order effects for all three questions. The second problem was to test data fitness with a model prediction called QQ equality and the data proved to be a good fit to the model. The purpose of the third problem was to examine the dependency of the q value derived from the model on a third question. Given that the QQ equality is a prediction which includes only two yes/no questions, an additional prediction was derived from the model which includes a third question and according to which, the q value is independent of a third question. The results showed a limitation in the model in explaining empirical data. A proposal was made how to expand the theory, so it would include models with three or more questions.