{"total":53,"rows":[{"id":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81,"area":null},{"id":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53,"area":"lr"},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46,"area":"safety"},{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2408.08631","title":"Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks","created":"2024-08-16","cited_by_count":28,"area":"lr"},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2505.09666","title":"System Prompt Optimization with Meta-Learning","created":"2025-05-14","cited_by_count":18,"area":null},{"id":"2407.12878","title":"Do LLMs have Consistent Values?","created":"2024-07-16","cited_by_count":14,"area":null},{"id":"2412.20545","title":"The Impact of Prompt Programming on Function-Level Code Generation","created":"2024-12-29","cited_by_count":13,"area":null},{"id":"2403.06591","title":"Academically intelligent LLMs are not necessarily socially intelligent","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2604.24698","title":"The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models","created":"2026-04-27","cited_by_count":8,"area":null},{"id":"2503.23243","title":"Evaluating how LLM annotations represent diverse views on contentious topics","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2408.10608","title":"BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2508.13047","title":"Using AI for User Representation: An Analysis of 83 Persona Prompts","created":"2025-08-18","cited_by_count":4,"area":null},{"id":"2605.29420","title":"When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2504.13868","title":"Diverse AI Personas Can Mitigate the Homogenization Effect in Human-AI Collaborative Ideation","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2601.21339","title":"Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2604.27624","title":"Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2501.15624","title":"Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets","created":"2025-01-26","cited_by_count":1,"area":null},{"id":"2506.15791","title":"TRUST: Transparent, Robust and Ultra-Sparse Trees","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2509.09727","title":"A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs","created":"2025-09-10","cited_by_count":1,"area":"agents"},{"id":"2511.19956","title":"Prompt Fairness: Sub-group Disparities in LLMs","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2603.15909","title":"Prompt Engineering for Scale Development in Generative Psychometrics","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.28643","title":"The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.30207","title":"Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit","created":"2026-05-28","cited_by_count":1,"area":"rag"},{"id":"2606.04057","title":"The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.18259","title":"Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2609.29509","title":"Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2404.08674","title":"Effects of Different Prompts on the Quality of GPT-4 Responses to Dementia Care Questions","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2511.03441","title":"CareMedEval dataset: Evaluating Critical Appraisal and Reasoning in the Biomedical Field","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2604.08986","title":"PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.17774","title":"Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25880","title":"Stemma: Induced Decision Regions Reveal LLM Provenance","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.12905","title":"Prompts in the Wild: A Large Analyzed Collection of Transactional Prompts in Code","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13786","title":"Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.00453","title":"mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.14803","title":"Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.25010","title":"Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.27110","title":"Feed the Panel Dimensions, Not Verdicts: Rubric-Decomposed Fusion of Vision-Language Aesthetic Judges","created":"2026-09-22","cited_by_count":0,"area":"mllm"},{"id":"2609.36239","title":"Cognitive Expert Language Models Better Align with the Corresponding Brain Systems","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00084","title":"Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.02829","title":"Clinical Concept Centers in LLMs","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}