[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84346-en":3,"doc-seo-84346-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84346,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Psychological Competence as a Missing Dimension in AI Evaluation","Current AI evaluation frameworks prioritize technical performance such as accuracy, robustness, reasoning, and policy compliance, which is necessary but incomplete for systems interacting directly with users through natural language. As human-facing AI becomes advisors, coaches, tutors, and companions, its responses shape cognition, emotion interpretation, belief formation, trust calibration, and decisions. The paper proposes psychological competence as a missing evaluation dimension, defining its capacity to support appropriate cognition, emotional interpretation, and behavioral decision-making, and outlines how it can be assessed via scenario-based probes, structured human evaluation, and model-assisted methods.","Psychological Competence as a Missing Dimension in AI Evaluation  \nMarcos Economides1 , Paul M. Sacher1,2 , Samuel Salzer1 , Alexis Michelle Abellar1 , Fendi Tsim1 , Antoine Ferrère1  \nAffiliations  \n1 Behavioral AI Institute, 2 Imperial College London  \nCorresponding author:  \nPaul M. Sacher  \n[p.sacher@imperial.ac.uk](p.sacher@imperial.ac.uk)  \nFunding  \nNo specific grant from any funding agency in the public, commercial, or not for profit sectors supported this work.  \nConflicts of interest  \nMarcos Economides is an Honorary Research Fellow at the Behavioral AI Institute, a not for profit organization, and provides research consulting services to digital mental health and AI companies. Paul M. Sacher is CEO of Sacher AI and Research Director of the Behavioral AI Institute. Antoine Ferrère is President of the Behavioral AI Institute and founder of  \nlumenx. Samuel Salzer is Operations Director of the Behavioral AI Institute and co-founder of Nuance Behavior. Alexis Michelle Abellar is an Honorary Associate Fellow for Behavioral AI Systems at the Behavioral AI Institute. Fendi Tsim is an Honorary Research Fellow at the  \nBehavioral AI Institute and co-founder of BehSci Meets AI. The authors declare no  \ncompeting financial interests related to this work.  \nData availability  \nNo datasets were generated or analyzed during this conceptual research.  \nAbstract  \nCurrent AI evaluation frameworks focus primarily on technical performance, including accuracy, robustness, reasoning ability, and policy compliance. These measures remain essential, but they are not sufficient for systems that interact directly with users through natural language. Human-facing AI systems are increasingly used as advisors, coaches, tutors, and companions. In these roles, their responses can shape how users reason, interpret emotions, form beliefs, calibrate trust, and make decisions. The relevant unit of evaluation is therefore not only the model, but the human-AI interaction.  \nThis paper introduces psychological competence as a missing dimension in AI evaluation.  \nWe define psychological competence as the capacity of a human-facing AI system to support user cognition, emotional interpretation, and behavioral decision-making in ways that are appropriate to the user, context, and purpose of the interaction. This includes interaction properties such as framing, tone, perceived authority, responsiveness, uncertainty handling, and conversational guidance. Existing evaluation approaches capture parts of this problem but rarely assess these psychological effects directly.  \nDrawing on behavioral science and human-AI interaction research, we outline a  \nconceptual framework for psychological competence and its core domains. Rather than proposing a specific benchmark, we define the construct, clarify its boundaries, and  \ndescribe how it may be assessed through scenario-based probes, structured human evaluation, and model-assisted evaluation methods. We argue that psychological  \ncompetence should become a core consideration for model providers, deploying organizations, researchers, and regulators concerned with the real-world effects of  \nhuman-facing AI systems.  \nIntroduction  \nArtificial intelligence systems are transitioning from tools that perform discrete computational tasks to systems that participate directly in human reasoning and decisionmaking. Human-facing AI systems increasingly act as tutors, advisors, coaches, and companions. In these roles, they influence how users interpret problems, regulate emotions, form beliefs, and choose between alternative actions.  \nThis transition demands a corresponding shift in how these systems are evaluated. Most AI benchmarks were developed to assess technical competence, including whether models produce correct answers, follow instructions, or solve reasoning tasks. These measures remain essential, but they primarily address a model-centric question: what can this system do? They are less equipped to answer a di","cbCaigCsn3oeKx2k","https://ap.wps.com/l/cbCaigCsn3oeKx2k","pdf",902175,1,22,"English","en",105,"# Abstract\n# Introduction\n## Shift from model-only benchmarks to interaction effects\n## Behavioral science mechanisms in human-facing AI\n## Risks of persuasive and feedback-driven influence","[{\"question\":\"What limitation do current AI evaluation frameworks have for human-facing systems?\",\"answer\":\"They focus mainly on technical output quality (accuracy, robustness, reasoning, policy compliance) and do not adequately measure how interaction affects users’ thinking, emotions, trust, and decisions.\"},{\"question\":\"How does the paper define psychological competence in AI evaluation?\",\"answer\":\"Psychological competence is the capacity of a human-facing AI system to support user cognition, emotional interpretation, and behavioral decision-making in ways that fit the user, context, and purpose of the interaction.\"},{\"question\":\"What kinds of interaction properties does psychological competence include?\",\"answer\":\"It includes factors such as framing, tone, perceived authority, responsiveness, uncertainty handling, and conversational guidance.\"}]",1784194971,55,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"psychological-competence-as-a-missing-dimension-in-ai-evaluation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/psychological-competence-as-a-missing-dimension-in-ai-evaluation/84346/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What limitation do current AI evaluation frameworks have for human-facing systems?","Question",{"text":74,"@type":75},"They focus mainly on technical output quality (accuracy, robustness, reasoning, policy compliance) and do not adequately measure how interaction affects users’ thinking, emotions, trust, and decisions.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the paper define psychological competence in AI evaluation?",{"text":79,"@type":75},"Psychological competence is the capacity of a human-facing AI system to support user cognition, emotional interpretation, and behavioral decision-making in ways that fit the user, context, and purpose of the interaction.",{"name":81,"@type":72,"acceptedAnswer":82},"What kinds of interaction properties does psychological competence include?",{"text":83,"@type":75},"It includes factors such as framing, tone, perceived authority, responsiveness, uncertainty handling, and conversational guidance.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]