Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, they often provide generic responses lacking emotional depth. Although large language models (LLMs) have the potential to create more human-like interactions, they still struggle to capture subtle emotions. This requires LLMs to be equipped with human-like adaptability and warmth. To fill this gap, we propose the MIND (Multi-agent INner Dialogue), a novel paradigm that provides more immersive psychological healing environments. Considering the strong generative and role-playing ability of LLM agents, we predefine an interactive healing framework and assign LLM agents different roles within the framework to engage in interactive inner dialogues with users, thereby providing an immersive healing experience. We conduct extensive human experiments in various real-world healing dimensions, and find that MIND provides a more user-friendly experience than traditional paradigms. This demonstrates that MIND effectively leverages the significant potential of LLMs in psychological healing.
Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We examine three LLMs, Llama-3-70B-instruct, Claude-3-Sonnet, and GPT-4o, on a range of QA tasks of varying difficulty, and show that models exhibit subtle differences from human patterns of overconfidence: less sensitive to task difficulty, and when prompted to answer based on different personas -- e.g., expert vs layman, or different race, gender, and ages -- the models will respond with stereotypically biased confidence estimations even though their underlying answer accuracy remains the same. Based on these observations, we propose Answer-Free Confidence Estimation (AFCE) to improve confidence calibration and LLM interpretability in these settings. AFCE is a self-assessment method that employs two stages of prompting, first eliciting only confidence scores on questions, then asking separately for the answer. Experiments on the MMLU and GPQA datasets spanning subjects and difficulty show that this separation of tasks significantly reduces overconfidence and delivers more human-like sensitivity to task difficulty.
Mohammed Marzuk T M, Vijayasarathy R, Madona Mathew
The act of posting a person's private photos or videos without their consent is known as revenge porn, and it is usually done to extort money or seek revenge. According to a 2010 cybercrime survey, about 18.3% of women were unaware that they were victims of revenge porn. In densely populated countries like India, such incidents are more likely, yet there is no specific law addressing revenge porn. This study used purposive sampling with a sample size of 200 unmarried women from Tamil Nadu aged 18 to 30. The survey results show that more than 50% had never heard the term "revenge porn," and only about 5% had personally experienced it. About 40% believed the victim was at fault, while 43.5% were unsure whether pornographic websites should be banned. Around 11% admitted that they might upload explicit content as revenge, and 8.5% felt that due to cultural taboos around sex, society tends to blame the victim. Police officers should be trained in techniques for psychologically supporting victims. India, which ranks third globally in cybercrime, must adopt better preventive measures. Public awareness and targeted legal reforms could play a major role in reducing such crimes.
Spaceflight is an isolated and confined environment (ICE) that exposes astronauts to psychological hazards, such as stress, danger, and monotony. Virtual reality (VR) and artificial intelligence (AI) technologies can serve as psychological countermeasures as they can digitally simulate immersive environments, interactive companions, and therapeutic experiences. Our study employs a scoping literature review approach to identify what is currently known about the use and effectiveness of VR and AI-based interventions as psychological countermeasures to improve mood or emotional states in adults in space or other ICEs. Additionally, this review aimed to identify gaps in the knowledge base and whether a systematic review with meta-analysis was warranted. The review included studies where the intervention was used or intended for use in space or other extraterrestrial environments (ICE). Our search strategy yielded 19 studies from 3390 records across seven major databases. All studies focused on VR-based interventions, with no eligible AI-based intervention studies found. VR interventions were found to be effective for relaxation and improving mood, emergency training, as an interactive communication platform, for comparing interior designs, and for enhancing exercise. There were improvements for measures of mood and emotion\n (e.g., anxiety and stress); however, user preferences varied, and some instances of cybersickness were reported. A systematic review with meta-analysis is not recommended due to the heterogeneity of results. There is significant scope for further research into the use of VR for a wider range of mood and emotion variables using standardised assessment instruments. Additionally, the potential application of AI as a psychological countermeasure warrants further investigation.
Chayapatr Archiwaranguprok, Constanze Albrecht, Pattie Maes
et al.
As AI systems become increasingly integrated into daily life, their potential to exacerbate or trigger severe psychological harms remains poorly understood and inadequately tested. This paper presents a proactive methodology for systematically exploring psychological risks in simulated human-AI interactions based on documented real-world cases involving AI-induced or AI-exacerbated addiction, anorexia, depression, homicide, psychosis, and suicide. We collected and analyzed 18 reported real-world cases where AI interactions contributed to severe psychological outcomes. From these cases, we developed a process to extract harmful interaction patterns and assess potential risks through 2,160 simulated scenarios using clinical staging models. We tested four major LLMs across multi-turn conversations to identify where psychological risks emerge: which harm domains, conversation stages, and contexts reveal system vulnerabilities. Through the analysis of 157,054 simulated conversation turns, we identify critical gaps in detecting psychological distress, responding appropriately to vulnerable users, and preventing harm escalation. Regression analysis reveals variability across persona types: LLMs tend to perform worse with elderly users but better with low- and middle-income groups compared to high-income groups. Clustering analysis of harmful responses reveals a taxonomy of fifteen distinct failure patterns organized into four categories of AI-enabled harm. This work contributes a novel methodology for identifying psychological risks, empirical evidence of common failure modes across systems, and a classification of harmful AI response patterns in high-stakes human-AI interactions.
Bell's inequality is derived from three assumptions: measurement independence, outcome independence, and parameter independence. Among these, measurement independence, often taken for granted, holds that hidden variables are statistically uncorrelated with measurement settings. Under this assumption, the violation of Bell's inequality implies that either outcome independence or parameter independence fails to hold, meaning that local hidden variables do not exist. In this paper, we refer to this interpretive stance as the nonfactorizable position. In contrast, superdeterminism represents the view that measurement independence does not hold. Despite its foundational role, this assumption has received relatively little philosophical scrutiny. This paper offers a philosophical reassessment of measurement independence through three major frameworks in the philosophy of science: de Regt's contextual theory of scientific understanding, Kuhn's criteria for theory choice, and Lakatos's methodology of scientific research programmes. Using these lenses, we evaluate the two major responses to the violation of Bell's inequality, the nonfactorizable position and superdeterminism, and argue that the nonfactorizable position currently fares better across all three criteria. Beyond this binary, we introduce a spectrum of intermediate positions that allow for partial violations of measurement independence, modeled via mutual information. These positions modify the ``positive heuristic'' of superdeterminism, a crucial component in Lakatos's definition of research programmes, offering avenues for progressive research. This analysis reframes the debate surrounding Bell's inequality and illustrates how methodological tools can effectively guide theory evaluation in physics.
Este artigo apresenta parte dos resultados de uma pesquisa de mestrado, que teve como escopo a apreensão dos sentidos do trabalho docente durante o período das atividades remotas, na pandemia do novo coronavírus. Para tanto, parte-se do entendimento da Psicologia Histórico-Cultural de que o mundo objetivo possui sua expressão subjetiva, dado que constitui uma unidade objetivo-subjetiva. Tal unidade se traduz para os sujeitos como sentidos subjetivos, composto por processos afetivos e cognitivos. Para a produção dos dados, foram realizados cinco encontros de um grupo focal com quatro docentes do Ensino Médio de uma escola pública, localizada no interior de São Paulo, e para a análise utilizou-se a metodologia qualitativa dos Núcleos de Significação. Os resultados indicaram a constituição de dois núcleos: I) Contexto pandêmico e sofrimento docente e II) Questões estruturais e trabalho docente, ambos sintetizaram mediações, por meio das quais ficou demonstrado que a pandemia intensificou processos de sofrimento que já vinham acometendo professores e professoras, e que o uso das Tecnologias de Informação e Comunicação – TICs – contribuiu para a disseminação da ideologia neoliberal na Educação. O estudo consolidou a atividade como a gênese dos sentidos, os quais, por interferência das condições pandêmicas, materializaram o esvaziamento do trabalho docente.
Conversational search offers an easier and faster alternative to conventional web search, while having downsides like lack of source verification. Research has examined performance disparities between these two systems in different settings. However, little work has considered the effects of variations within a given search task. We hypothesize that psychological distance - one's perceived closeness to a target event - affects information needs in search tasks, and investigate the corresponding effects on user preferences between web and conversational search systems. We find that with greater psychological distances, users perceive conversational search as more credible, useful, enjoyable, and easy to use, and demonstrate increased preference for this system. We reveal qualitative reasons for these differences and provide design implications for search system designers.
Recently, the demand for psychological counseling has significantly increased as more individuals express concerns about their mental health. This surge has accelerated efforts to improve the accessibility of counseling by using large language models (LLMs) as counselors. To ensure client privacy, training open-source LLMs faces a key challenge: the absence of realistic counseling datasets. To address this, we introduce Cactus, a multi-turn dialogue dataset that emulates real-life interactions using the goal-oriented and structured approach of Cognitive Behavioral Therapy (CBT). We create a diverse and realistic dataset by designing clients with varied, specific personas, and having counselors systematically apply CBT techniques in their interactions. To assess the quality of our data, we benchmark against established psychological criteria used to evaluate real counseling sessions, ensuring alignment with expert evaluations. Experimental results demonstrate that Camel, a model trained with Cactus, outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent. We make our data, model, and code publicly available.
Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles.Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions.We validated our framework using the D4 dataset. First, we created a public ECAs dataset through batch simulations based on D4. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines. The source code and dataset are available at https://github.com/AIR-DISCOVER/ECAs-Dataset.
Suicide and suicidal behaviors remain significant challenges for public policy and healthcare. In response, psychological support hotlines have been established worldwide to provide immediate help to individuals in mental crises. The effectiveness of these hotlines largely depends on accurately identifying callers' emotional states, particularly underlying negative emotions indicative of increased suicide risk. However, the high demand for psychological interventions often results in a shortage of professional operators, highlighting the need for an effective speech emotion recognition model. This model would automatically detect and analyze callers' emotions, facilitating integration into hotline services. Additionally, it would enable large-scale data analysis of psychological support hotline interactions to explore psychological phenomena and behaviors across populations. Our study utilizes data from the Beijing psychological support hotline, the largest suicide hotline in China. We analyzed speech data from 105 callers containing 20,630 segments and categorized them into 11 types of negative emotions. We developed a negative emotion recognition model and a fine-grained multi-label classification model using a large-scale pre-trained model. Our experiments indicate that the negative emotion recognition model achieves a maximum F1-score of 76.96%. However, it shows limited efficacy in the fine-grained multi-label classification task, with the best model achieving only a 41.74% weighted F1-score. We conducted an error analysis for this task, discussed potential future improvements, and considered the clinical application possibilities of our study. All the codes are public available.
We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in two social dilemmas: the repeated Prisoners Dilemma and the one-shot Dictator Game. Using a within-subject experimental design, we used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. We tested our research question by manipulating the part of our prompt which was used to create a simulated persona with different cooperative and competitive stances. We then assessed the resulting simulacras' level of cooperation in each social dilemma, taking into account the effect of different partner conditions for the repeated game. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour, particularly in the one-shot game. There is some evidence of behaviour resembling conditional reciprocity for the cooperative simulacra in the repeated game, and for the later version of the model there is evidence of altruistic behaviour. Our study has potential implications for using LLM chatbots in task environments that involve cooperation, e.g. using chatbots as mediators and facilitators in public-goods negotiations.
This study puts forward a conceptual model linking interpersonal influences' impact on Employee Engagement, Psychological contracts, and Human Resource Practices. It builds on human and social capital, as well as the social exchange theory (SET), projecting how interpersonal influences can impact the psychological contract (PC) and employee engagement (EE) of employees. This research analyzes the interpersonal influences of Wasta in the Middle East, Guanxi in China, Jeitinho in Brazil, Blat in Russia, and Pulling Strings in England. Interpersonal influences draw upon nepotism, favoritism, and corruption in organizations in many countries. This paper draws on the qualitative methods of analyzing previous theories. It uses the Model Paper method of predicting relationships by examining the question of how do interpersonal influences impact employee engagement and psychological contract?. It is vital to track the effects of interpersonal influences on PC and EE, acknowledging that the employer can either empower or disengage our human capital.
Every-day acoustical environments are often complex, typically comprising one attended target sound in the presence of interfering sounds (e.g., disturbing conversations) and reverberation. Here we assessed binaural detection thresholds and (supra-threshold) binaural audio quality ratings of four distortions types: spectral ripples, non-linear saturation, intensity and spatial modifications applied to speech, guitar, and noise targets in such complex acoustic environments (CAEs). The target and (up to) two masker sounds were either co-located as if contained in a common audio stream, or were spatially separated as if originating from different sound sources. The amount of reverberation was systematically varied. Masker and reverberation had a significant effect on the distortion-detection thresholds of speech signals. Quality ratings were affected by reverberation, whereas the effect of maskers depended on the distortion. The results suggest that detection thresholds and quality ratings for distorted speech in anechoic conditions are also valid for rooms with mild reverberation, but not for moderate reverberation. Furthermore, for spectral ripples, a significant relationship between the listeners’ individual detection thresholds and quality ratings was found. The current results provide baseline data for detection thresholds and audio quality ratings of different distortions of a target sound in CAEs, supporting the future development of binaural auditory models.
O escopo deste artigo é duplo. Primeiro, pretende apresentar um panorama histórico e contextual de implantação da nova Base Comum Curricular (BNCC) para o ensino básico sobretudo no que diz respeito à filosofia como componente curricular. Segundo, diante deste cenário de reforma da educação básica e da pedagogia oficial das competências e habilidades, objetiva propor uma filosofia da educação inspirada em Spinoza que aponte e oriente uma pedagogia onde o acompanhamento didático do erro é o ponto de partida da prática docente. Para tanto, dividimos este artigo em duas partes: na primeira, desenhamos o mapa legal onde se insere o ensino de filosofia; na segunda, discutimos os princípios da teoria do conhecimento spinozano no sentido de uma construção e justificação de uma pedagogia do acompanhamento do erro. Com isso, entendemos que a formulação de uma pedagogia inspirada em Spinoza é uma (dentre muitas outras) resposta possível e plausível para às exigências da BNCC, já que a emenda do intelecto pode ser entendida como uma “transcompetência” e, portanto, servir de referência para todas as competências propostas.
El presente artículo discute la obra pseudónima de Kierkegaard “El reflejo de lo trágico antiguo en lo trágico moderno”. El joven esteta A traza una distinción entre la “culpa antigua” y la “culpa moderna”. A utiliza esta distinción para formular una potente crítica a la ética moderna. No obstante, dicha polémica contra los conceptos éticos de la Modernidad no implican un retorno a la moralidad trágica antigua.