Agrima Seth, Monojit Choudhary, Sunayana Sitaram
et al.
Representational bias in large language models (LLMs) has predominantly been measured through single-response interactions and has focused on Global North-centric identities like race and gender. We expand on that research by conducting a systematic audit of GPT-4 Turbo to reveal how deeply encoded representational biases are and how they extend to less-explored dimensions of identity. We prompt GPT-4 Turbo to generate over 7,200 stories about significant life events (such as weddings) in India, using prompts designed to encourage diversity to varying extents. Comparing the diversity of religious and caste representation in the outputs against the actual population distribution in India as recorded in census data, we quantify the presence and "stickiness" of representational bias in the LLM for religion and caste. We find that GPT-4 responses consistently overrepresent culturally dominant groups far beyond their statistical representation, despite prompts intended to encourage representational diversity. Our findings also suggest that representational bias in LLMs has a winner-take-all quality that is more biased than the likely distribution bias in their training data, and repeated prompt-based nudges have limited and inconsistent efficacy in dislodging these biases. These results suggest that diversifying training data alone may not be sufficient to correct LLM bias, highlighting the need for more fundamental changes in model development. Dataset and Codebook: https://github.com/agrimaseth/How-Deep-Is-Representational-Bias-in-LLMs
Maciej Besta, Shriram Chandran, Robert Gerstenberger
et al.
We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.
Large language models (LLMs) are rapidly being adopted across psychology, serving as research tools, experimental subjects, human simulators, and computational models of cognition. However, the application of human measurement tools to these systems can produce contradictory results, raising concerns that many findings are measurement phantoms--statistical artifacts rather than genuine psychological phenomena. In this Perspective, we argue that building a robust science of AI psychology requires integrating two of our field's foundational pillars: the principles of reliable measurement and the standards for sound causal inference. We present a dual-validity framework to guide this integration, which clarifies how the evidence needed to support a claim scales with its scientific ambition. Using an LLM to classify text may require only basic accuracy checks, whereas claiming it can simulate anxiety demands a far more rigorous validation process. Current practice systematically fails to meet these requirements, often treating statistical pattern matching as evidence of psychological phenomena. The same model output--endorsing "I am anxious"--requires different validation strategies depending on whether researchers claim to measure, characterize, simulate, or model psychological constructs. Moving forward requires developing computational analogues of psychological constructs and establishing clear, scalable standards of evidence rather than the uncritical application of human measurement tools.
The article is dedicated to the 85th anniversary of Viktor P. Sheinov, a Belarusian-Russian scientist, Doctor of Sociological Sciences, Candidate of Physical and Mathematical Sciences, Academician of the International Academy of Information Technologies. The author believes that attention to Viktor P. Sheynov’s phenomenon is important not only from the point of view of the contribution of its bearer to various areas of intellectual activity, but also in connection with the search for resources for the renewal of domestic humanitarian science, and the significance of precedents for its effective implementation.
Mohammad Amin Abbasi, Farnaz Sadat Mirnezami, Hassan Naderi
This paper explores the intersection of psychology and artificial intelligence through the development and evaluation of specialized Large Language Models (LLMs). We introduce PsychoLex, a suite of resources designed to enhance LLMs' proficiency in psychological tasks in both Persian and English. Key contributions include the PsychoLexQA dataset for instructional content and the PsychoLexEval dataset for rigorous evaluation of LLMs in complex psychological scenarios. Additionally, we present the PsychoLexLLaMA model, optimized specifically for psychological applications, demonstrating superior performance compared to general-purpose models. The findings underscore the potential of tailored LLMs for advancing psychological research and applications, while also highlighting areas for further refinement. This research offers a foundational step towards integrating LLMs into specialized psychological domains, with implications for future advancements in AI-driven psychological practice.
Research into the external behaviors and internal mechanisms of large language models (LLMs) has shown promise in addressing complex tasks in the physical world. Studies suggest that powerful LLMs, like GPT-4, are beginning to exhibit human-like cognitive abilities, including planning, reasoning, and reflection. In this paper, we introduce a research line and methodology called LLM Psychology, leveraging human psychology experiments to investigate the cognitive behaviors and mechanisms of LLMs. We migrate the Typoglycemia phenomenon from psychology to explore the "mind" of LLMs. Unlike human brains, which rely on context and word patterns to comprehend scrambled text, LLMs use distinct encoding and decoding processes. Through Typoglycemia experiments at the character, word, and sentence levels, we observe: (I) LLMs demonstrate human-like behaviors on a macro scale, such as lower task accuracy and higher token/time consumption; (II) LLMs exhibit varying robustness to scrambled input, making Typoglycemia a benchmark for model evaluation without new datasets; (III) Different task types have varying impacts, with complex logical tasks (e.g., math) being more challenging in scrambled form; (IV) Each LLM has a unique and consistent "cognitive pattern" across tasks, revealing general mechanisms in its psychology process. We provide an in-depth analysis of hidden layers to explain these phenomena, paving the way for future research in LLM Psychology and deeper interpretability.
Artificial Intelligence (AI) is one of today's most relevant emergent technologies. In view thereof, this paper proposes that more attention should be paid to the philosophical aspects of AI technology and its use. It is argued that this deficit is generally combined with philosophical misconceptions about the growth of knowledge. To identify these misconceptions, reference is made to the ideas of the philosopher of science Karl Popper and the physicist David Deutsch. The works of both thinkers aim against mistaken theories of knowledge, such as inductivism, empiricism, and instrumentalism. This paper shows that these theories bear similarities to how current AI technology operates. It also shows that these theories are very much alive in the (public) discourse on AI, often called Bayesianism. In line with Popper and Deutsch, it is proposed that all these theories are based on mistaken philosophies of knowledge. This includes an analysis of the implications of these mistaken philosophies for the use of AI in science and society, including some of the likely problem situations that will arise. This paper finally provides a realistic outlook on Artificial General Intelligence (AGI) and three propositions on A(G)I and philosophy (i.e., epistemology).
Leveraging the synergy between causal knowledge graphs and a large language model (LLM), our study introduces a groundbreaking approach for computational hypothesis generation in psychology. We analyzed 43,312 psychology articles using a LLM to extract causal relation pairs. This analysis produced a specialized causal graph for psychology. Applying link prediction algorithms, we generated 130 potential psychological hypotheses focusing on `well-being', then compared them against research ideas conceived by doctoral scholars and those produced solely by the LLM. Interestingly, our combined approach of a LLM and causal graphs mirrored the expert-level insights in terms of novelty, clearly surpassing the LLM-only hypotheses (t(59) = 3.34, p=0.007 and t(59) = 4.32, p<0.001, respectively). This alignment was further corroborated using deep semantic analysis. Our results show that combining LLM with machine learning techniques such as causal knowledge graphs can revolutionize automated discovery in psychology, extracting novel insights from the extensive literature. This work stands at the crossroads of psychology and artificial intelligence, championing a new enriched paradigm for data-driven hypothesis generation in psychological research.
Psychological trait estimation from external factors such as movement and appearance is a challenging and long-standing problem in psychology, and is principally based on the psychological theory of embodiment. To date, attempts to tackle this problem have utilized private small-scale datasets with intrusive body-attached sensors. Potential applications of an automated system for psychological trait estimation include estimation of occupational fatigue and psychology, and marketing and advertisement. In this work, we propose PsyMo (Psychological traits from Motion), a novel, multi-purpose and multi-modal dataset for exploring psychological cues manifested in walking patterns. We gathered walking sequences from 312 subjects in 7 different walking variations and 6 camera angles. In conjunction with walking sequences, participants filled in 6 psychological questionnaires, totalling 17 psychometric attributes related to personality, self-esteem, fatigue, aggressiveness and mental health. We propose two evaluation protocols for psychological trait estimation. Alongside the estimation of self-reported psychological traits from gait, the dataset can be used as a drop-in replacement to benchmark methods for gait recognition. We anonymize all cues related to the identity of the subjects and publicly release only silhouettes, 2D / 3D human skeletons and 3D SMPL human meshes.
Taking the formal analogies between black holes and classical thermodynamics seriously seems to first require that classical thermodynamics applies to relativistic regimes. Yet, by scrutinizing how classical temperature is extended into special relativity, I argue that it falls apart. I examine four consilient procedures for establishing classical temperature - the Carnot process, the thermometer, kinetic theory, and black-body radiation. I show how their relativistic counterparts demonstrate no such consilience in defining relativistic temperature. Hence, classical temperature does not appear to survive a relativistic extension. I suggest two interpretations for this situation - eliminativism akin to simultaneity, or pluralism akin to rotation.
Given the strong mimetic and dramatic qualities found in Judith the authors make the suggestion that perhaps, before LXX Judith became a fixed, written text, the basic fabula might well have been part of an oral tradition. The authors accept that an appropriately written dramatic work, whether transmitted through reading or an oral presentation, by means of its performative qualities, has the potential to achieve immediacy. Here, the audience may become captivated with its own familiarity and memory of popular, communally shared narratives. Accordingly, this article attempts to find evidence in the Greek text of LXX Judith for a possible oral precursor. In this context, corroboration is sought for the employment of verbal aspect and mood of the Greek language as well as instances of drama, theatrics, bodily gestures, mnemonic devices or special emphasis on the employment of the senses such as sight, taste and smell. The authors suggest that based on an analysis of the text of Chapter 13, there is much circumstantial evidence for the Judith fabula once being an oral narrative – one that embodies the dramatic and even encourages audience participation. This characteristic strongly suggests the removal of the fourth wall – the notion of an imaginary boundary between any fictional work and its audience.
Contribution: This article shows that Judith 13 is indeed the climax of the narrative. However, it goes further. It is a vivid scene with various performative aspects. There are props, dialogue and audience participation. This research is cutting-edge and paves the way for new explorations.
The article aims to reveal the main features of the Bolshevik project to build
the Kingdom of Reason in the USSR, associated with the radical reformatting of the relationship between the rational and irrational in the establishment of the socialist society. Theoretical sources include the works of Karl Marx and Friedrich Engels, linking the construction of a new communist society to the demystification of social relations and the elimination of alienation and reification; the writings of Vladimir Lenin and other prominent figures of the Soviet state, devoted to the organization of planned economy and the widespread implementation of rational management methods; and the works of the outstanding educator Anton Makarenko, aimed at developing and implementing the idea of educating a new Soviet person. The article posits Bolshevism (Leninism) as the Russian version of socialist transformation, inheriting its fundamental ideas from the French Enlightenment, including the concept of the Kingdom of Reason, manifested in the system of rationally organized planning, accounting, and control. However, in practice, the development of this system, taken to its extreme forms, gave rise to a number
of utopian projects that became embodiments of irrational thinking. Thus, the original idea to build the Kingdom of Reason underwent a transformation into its opposite. Nevertheless, the authors of the article believe that the Soviet model of a rationally organized social structure can be considered, if not fully realized, then overall a fairly successful project of building the Kingdom of Reason in a socialist state and methodologically correct sociopedagogical system for shaping a new person.
El objetivo general de este texto es revisar el humor violento a través de teorías y funciones del humor, en primer lugar. En segundo lugar, y en concreto, realizar una caracterización de los tipos o las formas, y las expresiones o los modos, en su práctica cotidiana en general, y especialmente en la enseñanza aprendizaje.
Esto se realizó con la participación de jóvenes universitarios que expresaron opiniones y relataron experiencias, a través de una encuesta de grupos de enfoque y de narraciones. Como principal resultado es posible afirmar la vigencia del humor violento e incluso su magnitud en nuestros días, en la vida y en el espacio educativo.
The purpose of this paper is to suggest additional aspects of social psychology that could help when making sense of autonomous agile teams. To make use of well-tested theories in social psychology and instead see how they replicated and differ in the autonomous agile team context would avoid reinventing the wheel. This was done, as an initial step, through looking at some very common agile practices and relate them to existing findings in social-psychological research. The two theories found that I argue could be more applied to the software engineering context are social identity theory and group socialization theory. The results show that literature provides social-psychological reasons for the popularity of some agile practices, but that scientific studies are needed to gather empirical evidence on these under-researched topics. Understanding deeper psychological theories could provide a better understanding of the psychological processes when building autonomous agile team, which could then lead to better predictability and intervention in relation to human factors.
Artykuł omawia księgozbiór Ignacego Józefa Działyńskiego (1754-1797), generała, uczestnika wojny polsko-rosyjskiej (1792) oraz insurekcji kościuszkowskiej, działacza patriotycznego, wściela dób ziemskich. Auto wykorzystał – „Regestr rzeczy różnych po niegdy JW Ignacym hrabi Działyńskim jenerale bywszych wojsk polskich i różnych orderów polskich kawalerze, pozostałych, jako to sukien, futer, sreber, klejnotów i innych ruchomości, w ten regestr sprawiedliwie, nic nie opuszczając, wciągnionych, na groncie dóbr wsi Szumska przez uproszonych do tego dzieła przyjaciół, roku 1797 dnia 26 miesiąca nowembra [!] spisany” – przechowywany w Bibliotece Narodowej w spuściźnie Aleksandra Czołowskiego.
Bibliography. Library science. Information resources, History
The behavior coordinate system and the ideal individual model are presented. The behavior state of an ideal individual is assumed to be represented by a behavior state function. Based on the ideal individual model, the behavior coordinate system and the quantum probability, a novel quantum theory of psychology is offered here in a different way. It can give some enlightening viewpoints through which some phenomena can be discussed from a different perspective.
Empirical studies form an integral part of visualization research. Not only can they facilitate the evaluation of various designs, techniques, systems, and practices in visualization, but they can also enable the discovery of the causalities explaining why and how visualization works. This state-of-the-art report focuses on controlled and semi-controlled empirical studies conducted in laboratories and crowd-sourcing environments. In particular, the survey provides a taxonomic analysis of over 129 empirical studies in the visualization literature. It juxtaposes these studies with topic developments between 1978 and 2017 in psychology, where controlled empirical studies have played a predominant role in research. To help appreciate this broad context, the paper provides two case studies in detail, where specific visualization-related topics were examined in the discipline of psychology as well as the field of visualization. Following a brief discussion on some latest developments in psychology, it outlines challenges and opportunities in making new discoveries about visualization through empirical studies.
Research has shown that the maturity of small workgroups from a psychological perspective is intimately connected to team agility. We, therefore, tested if agile team members appreciated group development psychology training. Our results show that the participating teams seem to have a very positive view of group development training and state that they now have a new way of thinking about teamwork and new tools to deal with team-related problems. We, therefore, see huge potential in training agile teams in group development psychology since the positive effects might span over the entire software development organization.