arXiv subjects

Johan F. Hoorn

Publications and source records attributed to Johan F. Hoorn.

12 recordsLinked to original sources

arXiv2026

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored. In this work, we introduce relation-aware emotional support conversation, a new task that evaluates whether LLMs can capture and utilize the evolving dynamics of relationships to offer more effective emotional support. We construct RESCUE (Relation-aware Emotional Support Conversation Understanding and Evaluation Benchmark) from real couple and family interview conversations, containing 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video. Based on rich annotations of socio-emotional and support-related dynamics, RESCUE defines six tasks that evaluate two core capabilities required for relation-aware emotional support: Relational Understanding and Relation-Sensitive Support. Experiments with ten LLMs show that current models perform relatively well on tasks relying on local emotional or intervention cues, but struggle with relation-intensive tasks such as relation pattern prediction, viewpoint prediction, and support strategy prediction. These findings reveal the limitations of current LLMs in modeling interpersonal relations and making relation-sensitive support decisions.

cs.AI↗

arXiv2026

Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics

Large Language Models (LLMs) are increasingly deployed in diverse cultural contexts, yet their ability to master aesthetic stylistics, i.e., the strategic use of language to evoke cultural resonance, remains underexplored. We curate C4STYLI, a benchmark of highly stylized translated movie titles and advertising slogans from Hong Kong and the Chinese Mainland, to evaluate LLMs via the lens of behavioral recognition and productive competence. Extensive evaluations show that LLMs differ from humans in stylistic recognition, and this recognition ability varies across text domains. In addition, stylistic recognition and generation performance in LLMs are not consistently aligned. To further examine whether LLMs genuinely capture stylistic information in stylistic recognition, we conduct structural ablation with logistic regression probes. We find that, in the Hong Kong setting, stylistic recognition in LLMs relies primarily on surface-level linguistic information rather than stylistic structure. This suggests limited sensitivity to Hong Kong-specific stylistic structure.

cs.CL↗

arXiv2026

Epistemic reflections on AI answering our questions: overwatch, erudite, logician, interlocutor

Currently, there is a trend for the wider public to rely on LLMs for financial or legal consultation, medical and mental support (Chatterji et al., 2025), often accepting the advice provided without necessarily seeking logical verification or empirical validation. While one might be fortunate enough to encounter a model with a particularly solid 'ground truth' or with auxiliary logic-symbolic reasoning capabilities, it remains a somewhat uncertain endeavour. Output is simply taken at face value, without further question. Yet, careless reliance on AI to answer our questions and to judge our output is a violation of Grice's Maxim of Quality as well as a violation of Lemoine's legal Maxim of Innocence. A low-sensitivity plagiarism scanner may produce a Type II error by failing to detect difference (the null hypothesis wrongly maintained). The fallacy of affirming the consequent occurs when the failure to detect difference is then interpreted as evidence of equivalence or demonstration of AI authorship. If the test is specified so that 'AI-generated' is effectively treated as the default H0, then a finding of 'no difference from AI' is taken as support for that null. Such a mis-specified test results in students being treated as guilty (AI/plagiarism) unless suspects can generate sufficient detectable difference from AI output, which yields false accusations under a fair null hypothesis (that the student wrote the work). To avoid LLMs becoming a sorcerer's apprentice, knowledge is required about which inference systems are or should become integrated for an LLM to become a trustworthy sparring partner. We end on a wider perspective where the formalisation of the observer effect shows that uncertainty, classification, and interpretation are already shaped by the human or artificial agency's belief system, affective state, and tolerance for ambiguity, rather than at the stage of LLM output.

cs.CY↗

arXiv2026

Foresight Optimization for Strategic Reasoning in Large Language Models

Reasoning capabilities in large language models (LLMs) have generally advanced significantly. However, it is still challenging for existing reasoning-based LLMs to perform effective decision-making abilities in multi-agent environments, due to the absence of explicit foresight modeling. To this end, strategic reasoning, the most fundamental capability to anticipate the counterpart's behaviors and foresee its possible future actions, has been introduced to alleviate the above issues. Strategic reasoning is fundamental to effective decision-making in multi-agent environments, yet existing reasoning enhancement methods for LLMs do not explicitly capture its foresight nature. In this work, we introduce Foresight Policy Optimization (FoPO) to enhance strategic reasoning in LLMs, which integrates opponent modeling principles into policy optimization, thereby enabling explicit consideration of both self-interest and counterpart influence. Specifically, we construct two curated datasets, namely Cooperative RSA and Competitive Taboo, equipped with well-designed rules and moderate difficulty to facilitate a systematic investigation of FoPO in a self-play framework. Our experiments demonstrate that FoPO significantly enhances strategic reasoning across LLMs of varying sizes and origins. Moreover, models trained with FoPO exhibit strong generalization to out-of-domain strategic scenarios, substantially outperforming standard LLM reasoning optimization baselines.

cs.CL↗

arXiv2026

Observer effect modulates classification in a quantum epistemic framework

The observer effect in quantum physics states that observation inevitably influences the system being observed. This work introduces an epistemic framework that treats the observer as an integral part of sensory information processing within entangled quantum systems, leading to subjective and probabilistic observation and inference. We propose fuzzy instance classification by encoding sensory input to align with the observer's pre-existing beliefs in a feature-attribute-truth value hierarchical model as 'bells' of quantum oscillators whose states represent the degree of activation, associated with quantum probability. We demonstrate that within this framework, sensory data evolve via interaction with quantum-based observer states during the pre-decision phase, as described by the Lindblad master equation, and are then classified adaptively using positive operator-valued measures (POVM). The POVM enables the customisable parametrisation of measures of concurrent similarity and dissimilarity, facilitating subjectivity of perceptual associations and asymmetric cognition. Additionally, the observer's position on a sceptic-believer spectrum determines their robustness to noisy perceptions in ambiguous matching, balancing precision and flexibility. We show that sensory information becomes intricately entangled with observer states, yielding a wide array of probabilistic classification results. This framework lays the groundwork for a quantum probability-based understanding of the observer effect in cognitive processes, providing a formal basis for subjective interpretation not as a flaw in observation, but as a fundamental consequence of the observer-system interaction with quantum properties and correlations.

quant-ph↗

arXiv2026

Correlation of divergency: c-delta. Being different in a similar way or not

This paper introduces the correlation-of-divergency coefficient, c-delta, a custom statistical measure designed to quantify the similarity of internal divergence patterns between two groups of values. Unlike conventional correlation coefficients such as Pearson or Spearman, which assess the association between paired values, c-delta evaluates whether the way values differ within one group is mirrored in another. The method involves calculating, for each value, its divergence from all other values in its group, and then comparing these patterns across the two groups (e.g., human vs machine intelligence). The coefficient is normalised by the average root mean square divergence within each group, ensuring scale invariance. Potential applications of c-delta span quantum physics, where it can compare the spread of measurement outcomes between quantum systems, as well as fields such as genetics, ecology, psychometrics, manufacturing, machine learning, and social network analysis. The measure is particularly useful for benchmarking, clustering validation, and assessing the similarity of variability structures. While c-delta is not bounded between -1 and 1 and may be sensitive to outliers (but so is Pearson's r), it offers a new perspective for analysing internal variability and divergence. The article discusses the mathematical formulation, potential adaptations for complex data, and the interpretative considerations relevant to this alternative approach.

stat.ME↗

arXiv2025

A test statistic, $h^*$, for outlier analysis

Outlier analysis is a critical tool across diverse domains, from clinical decision-making to cybersecurity and talent identification. Traditional statistical outlier detection methods, such as Grubb's test and Dixon's Q, are predicated on the assumption of normality and often fail to reckon the meaningfulness of exceptional values within non-normal datasets. In this paper, we introduce the h* statistic, a novel parametric, frequentist approach for evaluating global outliers without the normality assumption. Unlike conventional techniques that primarily remove outliers to preserve statistical `integrity,' h* assesses the distinctiveness as phenomena worthy of investigation by quantifying a data point's extremity relative to its group as a measure of statistical significance analogous to the role of Student's t in comparing means. We detail the mathematical formulation of h* with tabulated confidence intervals of significance levels and extensions to Bayesian inference and paired analysis. The capacity of h* to discern between stable extraordinary deviations and values that merely appear extreme under conventional criteria is demonstrated using empirical data from a mood intervention study. A generalisation of h* is subsequently proposed, with individual weights assigned to differences for nuanced contextual description, and a variable sensitivity exponent for objective inference optimisation and subjective inference specification. The physical significance of an h*-recognised outlier is linked to the signature of unique occurrences. Our findings suggest that h* offers a robust alternative for outlier evaluation, enriching the analytical repertoire for researchers and practitioners by foregrounding the interpretative value of outliers within complex, real-world datasets. This paper is also a statement against the dominance of normality in celebration of the luminary and the lunatic alike.

stat.ME↗

arXiv2023

Theory of Robot Communication: II. Befriending a Robot over Time

In building on theories of Computer-Mediated Communication (CMC), Human-Robot Interaction, and Media Psychology (i.e. Theory of Affective Bonding), the current paper proposes an explanation of how over time, people experience the mediated or simulated aspects of the interaction with a social robot. In two simultaneously running loops, a more reflective process is balanced with a more affective process. If human interference is detected behind the machine, Robot-Mediated Communication commences, which basically follows CMC assumptions; if human interference remains undetected, Human-Robot Communication comes into play, holding the robot for an autonomous social actor. The more emotionally aroused a robot user is, the more likely they develop an affective relationship with what actually is a machine. The main contribution of this paper is an integration of Computer-Mediated Communication, Human-Robot Communication, and Media Psychology, outlining a full-blown theory of robot communication connected to friendship formation, accounting for communicative features, modes of processing, as well as psychophysiology.

cs.HC↗

arXiv2023

Theory of Robot Communication: I. The Medium is the Communication Partner

When people use electronic media for their communication, Computer-Mediated Communication (CMC) theories describe the social and communicative aspects of people's interpersonal transactions. When people interact via a remote-controlled robot, many of the CMC theses hold. Yet, what if people communicate with a conversation robot that is (partly) autonomous? Do the same theories apply? This paper discusses CMC theories in confrontation with observations and research data gained from human-robot communication. As a result, I argue for an addition to CMC theorizing when the robot as a medium itself becomes the communication partner. In view of the rise of social robots in coming years, I define the theoretical precepts of a possible next step in CMC, which I elaborate in a second paper.

cs.HC↗

arXiv2023

A robot's sense-making of fallacies and rhetorical tropes. Creating ontologies of what humans try to say

In the design of user-friendly robots, human communication should be understood by the system beyond mere logics and literal meaning. Robot communication-design has long ignored the importance of communication and politeness rules that are 'forgiving' and 'suspending disbelief' and cannot handle the basically metaphorical way humans design their utterances. Through analysis of the psychological causes of illogical and non-literal statements, signal detection, fundamental attribution errors, and anthropomorphism, we developed a fail-safe protocol for fallacies and tropes that makes use of Frege's distinction between reference and sense, Beth's tableau analytics, Grice's maxim of quality, and epistemic considerations to have the robot politely make sense of a user's sometimes unintelligible demands. Keywords: social robots, logical fallacies, metaphors, reference, sense, maxim of quality, tableau reasoning, epistemics of the virtual

cs.AI↗

arXiv2023

The Media Inequality, Uncanny Mountain, and the Singularity is Far from Near: Iwaa and Sophia Robot versus a Real Human Being

Design of Artificial Intelligence and robotics habitually assumes that adding more humanlike features improves the user experience, mainly kept in check by suspicion of uncanny effects. Three strands of theorizing are brought together for the first time and empirically put to the test: Media Equation (and in its wake, Computers Are Social Actors), Uncanny Valley theory, and as an extreme of human-likeness assumptions, the Singularity. We measured the user experience of real-life visitors of a number of seminars who were checked in either by Smart Dynamics' Iwaa, Hanson's Sophia robot, Sophia's on-screen avatar, or a human assistant. Results showed that human-likeness was not in appearance or behavior but in attributed qualities of being alive. Media Equation, Singularity, and Uncanny hypotheses were not confirmed. We discuss the imprecision in theorizing about human-likeness and rather opt for machines that 'function adequately.'

cs.RO↗

arXiv2019

Robot Affect: the Amygdala as Bloch Sphere

In the design of artificially sentient robots, an obstacle always has been that conventional computers cannot really process information in parallel, whereas the human affective system is capable of producing experiences of emotional concurrency (e.g., happy and sad). Another schism that has been in the way is the persistent Cartesian divide between cognition and affect, whereas people easily can reflect on their emotions or have feelings about a thought. As an essentially theoretical exercise, we posit that quantum physics at the basis of neurology explains observations in cognitive emotion psychology from the belief that the construct of reality is partially imagined (Im) in the complex coordinate space C^3. We propose a quantum computational account to mixed states of reflection and affect, while transforming known psychological dimensions into the actual quantum dynamics of electromotive forces. As a precursor to actual simulations, we show examples of possible robot behaviors, using Einstein-Podolsky-Rosen circuits. Keywords: emotion, reflection, modelling, quantum computing

cs.AI↗