Attitude

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 23

All topics

Population Fidelity: Evaluating Population Representativeness in LLMs
Sep 28, 2026Neemias B. da Silva, Martin Lukk, Ali Sutani +5Large Language Model Bias Demographics
University of Toronto, Canada · Federal University of Technology – Paran´a, Brazil
Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
Sep 22, 2026Sebastian CochinescuConfabulation Large Language Model Reliability
University of Bucharest
Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
Sep 14, 2026Bastiaan Bruinsma, Annika Fredén, Paul Röttger +2Ai-Assisted Writing Attitude
Chalmers University of Technology · University of Gothenburg · Lund University +1
Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations
Sep 12, 2026Doreen Jirak, Armeen Saroukanoff, Dirk van RooyMaritime Navigation Attitude
University of Antwerp, Paardenmarkt 94, 2000 Antwerp, Belgium · Antwerp Maritime Academy (AMA), Noordkasteel Oost 6, 2030 Antwerp, Belgium
Visual Framing for News Stance Detection via Image Generation
Sep 1, 2026Dahyun Lee, Jiyoung Han, Kunwoo ParkTask Framing Headlines
Soongsil University · KAIST
Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse
Aug 11, 2026Zhenyan Zheng, Yunyao Zhang, Junxi Sheng +2Emotion Recognition Sentiment
Huazhong University of Science and Technology
Trust and Its Betrayal under Three Representational Strategies
Jul 31, 2026Mihnea C. Moldoveanu, Joel A. C. BaumAI Trustworthiness Epistemic States
Rotman School of Management, University of Toronto
The persuasive power of large language models does not depend on their perceived national origin
Jul 31, 2026Ningzhi Liu, Yannic Hinrichs, Jonas R. KunstPersuasion Social Influence
Department of Psychology, University of Oslo, Norway · Department of Communication and Culture, BI Norwegian Business School, Norway
Rationale-Guided Knowledge Distillation for Cross-Lingual Stance Detection
Jul 21, 2026Qiuli Zhou, Jingyuan Yao, Shengeng Tang +3Cross-Topic Arabic Stance Detection Motion-Language Alignment
School of Foreign Studies, Hefei University of Technology, China · School of Computer Science and Information Engineering, Hefei University of Technology, China · School of Computer Science and Information Engineering, Hefei University of Technology +1
Perceived AGI: Believability as Dimensional Completeness, Not Capability
Jul 17, 2026Sebastian CochinescuAttitude Artificial Intelligence Systems
University of Bucharest
Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue
Jul 13, 2026Jihong ChenAttitude Confabulation
Beijing Etown Academy
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
Jul 10, 2026Hyein Park, Namho Kim, Junhwa KimFacial Expression Recognition Attitude
Dept. of AI Software Convergence, Konyang University · Korean Broadcasting System (KBS)
When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance
Jun 24, 2026Bo ChenRhetoric Attitude
Institute of Computing Technology, Chinese Academy of Sciences
Refusal Lives Downstream of Persona in Chat Models
Jun 24, 2026Viola Zhong, Qirui LiRefusals Persona Consistency
Independent · Department of Mathematics Pohang University of Science and Technology
Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs
Jun 3, 2026Farouq Sammour, Yuxin Zhang, Zhenyu ZhangSafety Claims Attitude
aDepartment of Construction Science, College of Architecture, Texas A&M University, College Station, USA
AI Technologies in Language Access: Attitudes Towards AI and the Human Value of Language Access Managers
May 19, 2026Miguel A. Jiménez-Crespo, Stephanie Rodriguez, Alejandro Jaume LosaHuman Values Attitude
Rutgers University/ Dept. of Spanish and Portuguese, 15 Seminary Pl 5th fl., New Brunswick, NJ, 07030, USA
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
May 14, 2026Joshua C. Yang, Maurice Flechtner, Damian Dailisan +1Deliberation Large Language Model Decisions
ETH Zurich · ETH Zurich and Centre for Democracy Studies Aarau, University of Zurich · Massachusetts Institute of Technology
AI-Automation Tooling in Computer Engineering Education: Mixed-Methods TAM/UTAUT Evidence for a General Acceptance Attitude
May 10, 2026Aung PyaeComputer Science Software Engineering
International School of Engineering, Faculty of Engineering Chulalongkorn University, Thailand
On the Emergence of Pendular Structure in Multi-Contact Locomotion
May 7, 2026Lingxue Lyu, Zihui LiuInverted Pendulum Torque
School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Aeronautics & Astronautics, Stanford University, Stanford, CA 94305, USA
A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection
Apr 29, 2026Genan Dai, Zini Chen, Yi Yang +1Attitude Authorship
School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China
Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
Apr 22, 2026Matthew James BuchanSycophancy Attitude
Independent Researcher, United Kingdom.
IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
Apr 17, 2026Christina Chance, Rebecca Pattichis, Arjun Subramonian +4Hate Speech Content Moderation
University of California Los Angeles, USA · Independent Researcher, USA
Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas
Jan 29, 2026Katherine Elkins, Jon ChunMoral Reasoning Task Framing
Kenyon College Gambier, OH

Sep 28, 2026, cs.CLJ/K move · Enter open · S save

Population Fidelity: Evaluating Population Representativeness in LLMs

Neemias B. da Silva, Martin Lukk, Ali Sutani, Abhishek Moturu+4

University of Toronto, Canada · Federal University of Technology – Paran´a, Brazil

Large Language Model Bias Demographics Populations Large Language Model Alignment Attitude Continual Fine-Tuning

Open paper AskPDF arXiv

Large language models (LLMs) show considerable potential in simulating human attitudes and preferences. Prior work finds that LLM-generated responses can compress the range of attitudes found within populations and misrepresent particular subgroups in ways that vary across models and topics. We introduce Population Fidelity, an evaluation framework that distinguishes key conditions required for a set of LLM-generated responses to represent a population. It incorporates three dimensions: group-level accuracy, the amount of between-group variation, and the structure of that variation. We demonstrate the framework's utility in two ways. First, we reproduce a prior study of "machine bias" in LLM survey responses and apply the framework to its models and more recent ones, showing that poor representation reflects not only insufficient between-group variation but also variation assigned to the wrong groups. Second, we evaluate one proposed approach to improving models' population representativeness: cultural fine-tuning. We find that cultural fine-tuning can improve alignment with the survey center without improving the representation of within-population differences, a distinction that measures of aggregate agreement do not capture. We argue that representing a population requires models to reproduce several features of human attitudinal variation simultaneously. Our framework organizes these features and provides reusable code, data, and trained models for evaluating population fidelity across substantive domains and assessing proposed alignment methods.

Momentum

Related topics

Latest papers 23