Human self-report questionnaires are increasingly used in NLP to benchmark and audit large language models (LLMs), from persona consistency to safety and bias assessments. Yet these instruments presume honest responding; in evaluative contexts, LLMs can instead gravitate toward socially preferred answers-a form of socially desirable responding (SDR)-biasing questionnaire-derived scores and downstream conclusions. We propose a psychometric framework to quantify and mitigate SDR in questionnaire-based evaluation of LLMs. To quantify SDR, the same inventory is administered under HONEST versus FAKE-GOOD instructions, and SDR is computed as a direction-corrected standardized effect size from item response theory (IRT)-estimated latent scores. This enables comparisons across constructs and response formats, as well as against human instructed-faking benchmarks. For mitigation, we construct a graded forced-choice (GFC) Big Five inventory by selecting 30 cross-domain pairs from an item pool via constrained optimization to match desirability. Across nine instruction-following LLMs evaluated on synthetic personas with known target profiles, Likert-style questionnaires show consistently large
Same/opposite relational responding, a fundamental aspect of human symbolic cognition, allows the flexible generalization of stimulus relationships based on minimal experience. In this study, we demonstrate the emergence of \textit{arbitrarily applicable} same/opposite relational responding within the Non-Axiomatic Reasoning System (NARS), a computational cognitive architecture designed for adaptive reasoning under uncertainty. Specifically, we extend NARS with an implementation of \textit{acquired relations}, enabling the system to explicitly derive both symmetric (mutual entailment) and novel relational combinations (combinatorial entailment) from minimal explicit training in a contextually controlled matching-to-sample (MTS) procedure. Experimental results show that NARS rapidly internalizes explicitly trained relational rules and robustly demonstrates derived relational generalizations based on arbitrary contextual cues. Importantly, derived relational responding in critical test phases inherently combines both mutual and combinatorial entailments, such as deriving same-relations from multiple explicitly trained opposite-relations. Internal confidence metrics illustrate strong
Biological cells are able to adapt their behaviour in response to environmental cues. Durotaxis is a phenomenon in which cells adjust their migration depending on the mechanical properties of a surrounding substrate. Although durotaxis has been studied more than two decades, basic cellular-scale mechanism of how cells regulate the motility responding to substrate stiffness remains to be elucidated. We address this issue by developing a theory utilising a mechanochemical model that integrates intracellular biochemical reactions with cellular deformation and substrate adhesion. Numerical analysis reveals that the characteristic speed and diffusion constant of cells change non-monotonically with respect to substrate stiffness, indicating the emergence of an optimal stiffness for migration. In addition, by introducing a memory effect that allows feedback from cell mechanics to the intracellular chemical reactions, the persistence time increases with substrate stiffness on a substrate softer than the optimal. We further investigate theoretically the origin of the non-monotonic dependence, that is comparable to the experimental observations, in terms of cell deformation and symmetry brea
Questionnaires in the behavioral sciences tend to be lengthy. However, literature suggests that survey length is a contributing factor to careless responding, with longer questionnaires yielding higher probability that participants start responding carelessly. Consequently, in long surveys a large number of participants may engage in careless responding, posing a major threat to internal validity. We propose a novel method for identifying the onset of careless responding (or an absence thereof) that searches for a changepoint in combined measurements of multiple dimensions in which carelessness may manifest, such as inconsistency and invariability. It is highly flexible, based on machine learning, and provides statistical guarantees for controlling the false positive rate. In simulation experiments, the proposed method achieves high accuracy in identifying carelessness onset and discriminates well between attentive and various types of careless responding, even when a large number of careless respondents are present. An empirical application highlights how identifying partial carelessness uncovers novel insights on careless responding behavior. Furthermore, we provide the freely av
Arbitrarily Applicable Relational Responding (AARR) is a cornerstone of human language and reasoning, referring to the learned ability to relate symbols in flexible, context-dependent ways. In this paper, we present a novel theoretical approach for modeling AARR within an artificial intelligence framework using the Non-Axiomatic Reasoning System (NARS). NARS is an adaptive reasoning system designed for learning under uncertainty. By integrating principles from Relational Frame Theory - the behavioral psychology account of AARR - with the reasoning mechanisms of NARS, we conceptually demonstrate how key properties of AARR (mutual entailment, combinatorial entailment, and transformation of stimulus functions) can emerge from the inference rules and memory structures of NARS. Two theoretical experiments illustrate this approach: one modeling stimulus equivalence and transfer of function, and another modeling complex relational networks involving opposition frames. In both cases, the system logically demonstrates the derivation of untrained relations and context-sensitive transformations of stimulus significance, mirroring established human cognitive phenomena. These results suggest th
The classic Bayesian persuasion model assumes a Bayesian and best-responding receiver. We study a relaxation of the Bayesian persuasion model where the receiver can approximately best respond to the sender's signaling scheme. We show that, under natural assumptions, (1) the sender can find a signaling scheme that guarantees itself an expected utility almost as good as its optimal utility in the classic model, no matter what approximately best-responding strategy the receiver uses; (2) on the other hand, there is no signaling scheme that gives the sender much more utility than its optimal utility in the classic model, even if the receiver uses the approximately best-responding strategy that is best for the sender. Together, (1) and (2) imply that the approximately best-responding behavior of the receiver does not affect the sender's maximal achievable utility a lot in the Bayesian persuasion problem. The proofs of both results rely on the idea of robustification of a Bayesian persuasion scheme: given a pair of the sender's signaling scheme and the receiver's strategy, we can construct another signaling scheme such that the receiver prefers to use that strategy in the new scheme more
Interpersonal communication plays a key role in managing people's emotions, especially on digital platforms. Studies have shown that people use social media and consume online content to regulate their emotions and find support for rest and recovery. However, these platforms are not designed for emotion regulation, which limits their effectiveness in this regard. To address this issue, we propose an approach to enhance Interpersonal Emotion Regulation (IER) on online platforms through content recommendation. The objective is to empower users to regulate their emotions while actively or passively engaging in online platforms by crafting media content that aligns with IER strategies, particularly empathic responding. The proposed recommendation system is expected to blend system-initiated and user-initiated emotion regulation, paving the way for real-time IER practices on digital media platforms. To assess the efficacy of this approach, a mixed-method research design is used, including the analysis of text-based social media data and a user survey. Digital applications has served as facilitators in this process, given the widespread recognition of digital media applications for Digit
Long-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization. As the community increasingly prioritizes the faithfulness of generated results, merely ensuring the accuracy of LCM outputs is insufficient, as it is quite challenging for humans to verify the results from the extremely lengthy context. Yet, although some efforts have been made to assess whether LCMs respond truly based on the context, these works either are limited to specific tasks or heavily rely on external evaluation resources like GPT4.In this work, we introduce L-CiteEval, a comprehensive multi-task benchmark for long-context understanding with citations, aiming to evaluate both the understanding capability and faithfulness of LCMs. L-CiteEval covers 11 tasks from diverse domains, spanning context lengths from 8K to 48K, and provides a fully automated evaluation suite. Through testing with 11 cutting-edge closed-source and open-source LCMs, we find that although these models show minor differences in their generated results, open-source models substantially trail behind their closed-source cou
We consider a repeated Stackelberg game setup where the leader faces a sequence of followers of unknown types and must learn what commitments to make. While previous works have considered followers that best respond to the commitment announced by the leader in every round, we relax this setup in two ways. Motivated by natural scenarios where the leader's reputation factors into how the followers choose their response, we consider followers with memory. Specifically, we model followers that base their response on not just the leader's current commitment but on an aggregate of their past commitments. In developing learning strategies that the leader can employ against such followers, we make the second relaxation and assume boundedly rational followers. In particular, we focus on followers employing quantal responses. Interestingly, we observe that the smoothness property offered by the quantal response (QR) model helps in addressing the challenge posed by learning against followers with memory. Utilizing techniques from online learning, we develop algorithms that guarantee $O(\sqrt{T})$ regret for quantal responding memory-less followers and $O(\sqrt{BT})$ regret for followers with
Industrial demand response (IDR) plays an important role in promoting the utilization of renewable energy (RE) in power systems. However, it will lead to power adjustments on the supply side, which is also a non-negligible factor in affecting RE utilization. To comprehensively analyze this impact while enhancing RE utilization, this paper proposes a power demand-supply cooperative response (PDSCR) strategy based on both day-ahead and intraday time scales. The day-ahead PDSCR determines a long-term scheme for responding to the predictable trends in RE supply. However, this long-term scheme may not be suitable when uncertain RE fluctuations occur on an intraday basis. Regarding intraday PDSCR, we formulate a profit-driven cooperation approach to address the issue of RE fluctuations. In this context, unreasonable profit distributions on the demand-supply side would lead to the conflict of interests and diminish the effectiveness of cooperative responses. To mitigate this issue, we derive multi-individual profit distribution marginal solutions (MIPDMSs) based on satisfactory profit distributions, which can also maximize cooperative profits. Case studies are conducted on an modified IEE
We simulate the bulge formation in very late-type dwarf galaxies from circumnuclear super star clusters (SSCs) moving in a responding cuspy dark matter halo (DMH). The simulations show that (1) the response of DMH to sinking of SSCs is detectable only in the region interior to about 200 pc. The mean logarithmic slope of the responding DM density profile over that area displays two different phases: the very early descent followed by ascent till approaching to 1.2 at the age of 2 Gyrs. (2) the detectable feedbacks of the DMH response on the bulge formation turned out to be very small, in the sense that the formed bulges and their paired nuclear cusps in the fixed and the responding DMH are basically the same, both are consistent with $HST$ observations. (3) the yielded mass correlation of bulges to their nuclear (stellar) cusps and the time evolution of cusps' mass are accordance with recent findings on relevant relations. In combination with the consistent effective radii of nuclear cusps with observed quantities of nuclear clusters, we believe that the bulge formation scenario that we proposed could be a very promising mechanism to form nuclear clusters.
Recently, improving the relevance and diversity of dialogue system has attracted wide attention. For a post x, the corresponding response y is usually diverse in the real-world corpus, while the conventional encoder-decoder model tends to output the high-frequency (safe but trivial) responses and thus is difficult to handle the large number of responding styles. To address these issues, we propose the Atom Responding Machine (ARM), which is based on a proposed encoder-composer-decoder network trained by a teacher-student framework. To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms. In other words, even a little of atom-mechanisms can make a mickle of molecule-mechanisms. The experiments demonstrate diversity and quality of the responses generated by ARM. We also present generating process to show underlying interpretability for the result.
T-cell receptor (TCR) repertoire data contain information about infections that could be used in disease diagnostics and vaccine development, but extracting that information remains a major challenge. Here we developed a statistical framework to detect TCR clone proliferation and contraction from longitudinal repertoire data. We applied this framework to data from three pairs of identical twins immunized with the yellow fever vaccine. We identified 500-1500 responding TCRs in each donor and validated them using three independent assays. While the responding TCRs were mostly private, albeit with higher overlap between twins, they could be well predicted using a classifier based on sequence similarity. Our method can also be applied to samples obtained post-infection, making it suitable for systematic discovery of new infection-specific TCRs in the clinic.
As autonomous vehicles advance toward driverless mobility, understanding and responding to passenger needs and intentions becomes increasingly important in the absence of a human driver. We propose Intent2Drive, a unified framework for holistic passenger intent understanding and passenger-aligned planning. Unlike existing methods that rely on explicit commands, Intent2Drive models passenger intent as a latent cognitive state inferred from language, personal attributes, emotions, behaviors, and situational context. To support this task, we construct the Holistic Passenger Intent Dataset (HPID) with structured annotations of explicit and implicit passenger-intent cues. A Theory-of-Mind-inspired Passenger Intent Reasoner (PIR) infers a Latent Passenger State (LPS) and converts it into a planner-compatible Passenger Intent Objective (PIO). We validate the downstream utility of PIO by conditioning an existing hierarchical planning pipeline at the route and trajectory levels. Experiments demonstrate that the proposed method understands and responds to passenger needs, enabling passenger-aligned driving while maintaining competitive closed-loop planning performance.
The majority of voice-based conversational agents still rely on pause-and-respond turn-taking, leaving interactions sounding stiff and robotic. We present RESPOND (Responsive Engagement Strategy for Predictive Orchestration and Dialogue), a framework that brings two staples of human conversation to agents: timely backchannels ("mm-hmm," "right") and proactive turn claims that can contribute relevant content before the speaker yields the conversational floor. Built on streaming ASR (Automatic Speech Recognition) and incremental semantics, RESPOND continuously predicts both when and how to interject, enabling fluid, listener-aware dialogue. A defining feature is its designer-facing controllability: two orthogonal dials, Backchannel Intensity (frequency of acknowledgments) and Turn Claim Aggressiveness (depth and assertiveness of early contributions), can be tuned to match the etiquette of contexts ranging from rapid ideation to reflective counseling. By coupling predictive orchestration with explicit control, RESPOND offers a practical path toward conversational agents that adapt their conversational footprint to social expectations, advancing the design of more natural and engaging
People respond to artificial intelligence chatbots (AICs) in highly variable ways. In this paper, we adapt Bronfenbrenner's theory into a heuristic framework for understanding this variation. The framework places the human user at the center while also placing the AI there and reconceptualizing the proximal processes as the repeated, reciprocal, and coadaptive interactions between the user and a personalized AIC. The surrounding systems identify the contextual factors that shape how the user experiences, interprets, responds to, and is changed by these interactions. Because stateful AICs learn from accumulated exchanges with their users and have memory, users are responding not only to an AIC but also to a version of the AIC that their own prior interactions have helped create. This extension preserves Bronfenbrenner's emphasis on proximal processes while accounting for the unique dynamics of personalized AICs. The resulting framework provides a structured map of where and how variation in human and AIC relationships arises, as well as having implications for researchers, practitioners, and AIC designers.
Large language models are increasingly used by participants on crowdsourcing platforms when responding to surveys, potentially undermining the validity of collected data. Our study aims to quantify the prevalence of this behavior and investigate methods to detect and prevent it. In a series of surveys (N = 250), we examined conditions such as platform choice, survey length, requests not to use AI, and disabling copy-paste functionality. We were able to identify distinct characteristics of LLM-assisted responses and found that their frequency varied widely, from under 10% on Prolific to over 80% on Mechanical Turk. Mitigation measures reduced LLM usage but did not necessarily improve data quality. No participants employed browser-use agents at the time of our survey, but we report on our own detection experiments. We recommend that researchers actively screen survey responses for LLM usage by recording and analyzing keystroke data and crafting instructions and questions aimed at AI.
Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement fine-tuning these rewards, CollabLLM goes beyond responding to user requests, and actively uncovers user intent and offers insightful suggestions-a key step towards more human-centered AI. We also devise a multiturn interaction benchmark with three challenging tasks such as document creation. CollabLLM significantly outperforms our baselines with averages of 18.5% higher task performance and 46.3% improved interactivity by LLM judges. Finally, we conduct a large user study with 201 judges, where CollabLLM increases user satisfaction by 17.6% and reduces user spent time by 10.4%.
As psychometric surveys are increasingly used to assess the traits of large language models (LLMs), the need for scalable survey item generation suited for LLMs has also grown. A critical challenge here is ensuring the construct validity of generated items, i.e., whether they truly measure the intended trait. Traditionally, this requires costly, large-scale human data collection. To make it efficient, we present a framework for virtual respondent simulation using LLMs. Our central idea is to account for mediators: factors through which the same trait can give rise to varying responses to a survey item. By simulating respondents with diverse mediators, we identify survey items that yield responses robustly correlated with intended traits across these mediators. Experiments on three psychological trait theories (Big5, Schwartz, VIA) show that our mediator generation methods and simulation framework effectively identify high-validity items. LLMs demonstrate the ability to generate plausible mediators from trait definitions and to simulate respondent behavior for item validation. Our problem formulation, metrics, methodology, and dataset open a new direction for cost-efficient survey d
Standardized surveys scale efficiently but sacrifice depth, while conversational interviews improve response quality at the cost of scalability and consistency. This study bridges the gap between these methods by introducing a framework for AI-assisted conversational interviewing. To evaluate this framework, we conducted a web survey experiment where 1,800 participants were randomly assigned to AI 'chatbots' which use large language models (LLMs) to dynamically probe respondents for elaboration and interactively code open-ended responses to fixed questions developed by human researchers. We assessed the AI chatbot's performance in terms of coding accuracy, response quality, and respondent experience. Our findings reveal that AI chatbots perform moderately well in live coding even without survey-specific fine-tuning, despite slightly inflated false positive errors due to respondent acquiescence bias. Open-ended responses were more detailed and informative, but this came at a slight cost to respondent experience. Our findings highlight the feasibility of using AI methods such as chatbots enhanced by LLMs to enhance open-ended data collection in web surveys.