{"total":147,"rows":[{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2406.03718","title":"Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning","created":"2024-06-06","cited_by_count":30,"area":null},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2310.11409","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25,"area":null},{"id":"2405.18027","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21,"area":null},{"id":"2509.10127","title":"Population-Aligned Persona Generation for LLM-based Social Simulation","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2309.03613","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","created":"2023-09-07","cited_by_count":20,"area":null},{"id":"2404.13957","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2402.07658","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","created":"2024-02-12","cited_by_count":18,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2508.19764","title":"Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance","created":"2025-08-27","cited_by_count":18,"area":null},{"id":"2505.04843","title":"Large Language Models are Autonomous Cyber Defenders","created":"2025-05-07","cited_by_count":15,"area":null},{"id":"2406.04064","title":"Ask LLMs Directly, \"What shapes your bias?\": Measuring Social Bias in Large Language Models","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2407.16470","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","created":"2024-07-23","cited_by_count":13,"area":null},{"id":"2407.08995","title":"Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs","created":"2024-07-12","cited_by_count":12,"area":null},{"id":"2512.12775","title":"Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions","created":"2025-12-14","cited_by_count":12,"area":null},{"id":"2503.17073","title":"A Study into Investigating Temporal Robustness of LLMs","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2311.09651","title":"\"It's not like Jarvis, but it's pretty close!\" -- Examining ChatGPT's Usage among Undergraduate Students in Computer Science","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2403.02756","title":"Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2402.17396","title":"Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2405.08008","title":"Iris: An AI-Driven Virtual Tutor For Computer Science Education","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2412.07448","title":"Efficient Dynamic Ensembling for Multiple LLM Experts","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2402.09546","title":"How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2402.18609","title":"ICE-SEARCH: A Language Model-Driven Feature Selection Approach","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8,"area":null},{"id":"2506.07947","title":"Statistical Hypothesis Testing for Auditing Robustness in Language Models","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2506.19352","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2403.18121","title":"ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2406.17287","title":"Predicting the Big Five Personality Traits in Chinese Counselling Dialogues Using Large Language Models","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2409.14202","title":"Mining Causality: AI-Assisted Search for Instrumental Variables","created":"2024-09-21","cited_by_count":7,"area":null},{"id":"2409.15687","title":"A Comprehensive Evaluation of Large Language Models on Mental Illnesses","created":"2024-09-24","cited_by_count":7,"area":null},{"id":"2503.10968","title":"Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms","created":"2025-03-14","cited_by_count":7,"area":null},{"id":"2503.22250","title":"Modeling Challenging Patient Interactions: LLMs for Medical Communication Training","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2508.03929","title":"MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework","created":"2025-08-05","cited_by_count":7,"area":null},{"id":"2403.12196","title":"Leveraging Large Language Models to Detect npm Malicious Packages","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2404.17443","title":"\"ChatGPT Is Here to Help, Not to Replace Anybody\" -- An Evaluation of Students' Opinions On Integrating ChatGPT In CS Courses","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2503.05565","title":"Evaluating open-source Large Language Models for automated fact-checking","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2406.05348","title":"Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets","created":"2024-06-08","cited_by_count":5,"area":null},{"id":"2406.12644","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2407.13717","title":"CoDefeater: Using LLMs To Find Defeaters in Assurance Cases","created":"2024-07-18","cited_by_count":5,"area":null},{"id":"2408.08892","title":"Leveraging Large Language Models for Enhanced Process Model Comprehension","created":"2024-08-08","cited_by_count":5,"area":null},{"id":"2411.07965","title":"SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2502.20864","title":"Do Language Models Understand Honorific Systems in Javanese?","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2503.16622","title":"Leveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2507.15025","title":"Survey of GenAI for Automotive Software Development: From Requirements to Executable Code","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2501.03508","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","created":"2025-01-07","cited_by_count":4,"area":null},{"id":"2503.05010","title":"Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.22040","title":"Navigating the Risks of Using Large Language Models for Text Annotation in Social Science Research","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2504.13656","title":"Do Prompt Patterns Affect Code Quality? A First Empirical Assessment of ChatGPT-Generated Code","created":"2025-04-18","cited_by_count":4,"area":null},{"id":"2507.19549","title":"AccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML Code","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2511.02458","title":"Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas","created":"2025-11-04","cited_by_count":4,"area":null},{"id":"2511.16883","title":"PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling","created":"2025-11-21","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":"2403.03585","title":"RouteExplainer: An Explanation Framework for Vehicle Routing Problem","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2501.09265","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2506.02480","title":"ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2506.04038","title":"Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2410.13029","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2502.04376","title":"MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2504.19734","title":"LLM-Assisted Automated Deductive Coding of Dialogue Data: Leveraging Dialogue-Specific Characteristics to Enhance Contextual Understanding","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2505.23191","title":"ExpeTrans: LLMs Are Experiential Transfer Learners","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.16150","title":"PRISON: Unmasking the Criminal Potential of Large Language Models","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2507.03009","title":"PDFMathTranslate: Scientific Document Translation Preserving Layouts","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2507.09839","title":"Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2508.01401","title":"MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2509.10685","title":"Pluralistic Alignment for Healthcare: A Role-Driven Framework","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2511.21218","title":"Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.00044","title":"When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applications","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2607.01103","title":"Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2402.18807","title":"On the Decision-Making Abilities in Role-Playing using Large Language Models","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2404.03732","title":"SHROOM-INDElab at SemEval-2024 Task 6: Zero- and Few-Shot LLM-Based Classification for Hallucination Detection","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2501.00224","title":"Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2501.06964","title":"Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives","created":"2025-01-12","cited_by_count":1,"area":null},{"id":"2505.24448","title":"Exploring the Impact of Occupational Personas on Domain-Specific QA","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2507.17948","title":"VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.19517","title":"Orchid: Orchestrating Context Across Creative Workflows with Generative AI","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2508.20217","title":"Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2510.20258","title":"Using Large Language Models for Abstraction of Planning Domains - Extended Version","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.20233","title":"REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.05858","title":"Prompting Science Report 4: Playing Pretend: Expert Personas Don't Improve Factual Accuracy","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2512.17270","title":"Understanding Generalization in Role-Playing Models via Information Theory","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.01320","title":"Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2601.22921","title":"Evaluating Large Language Models for Security Bug Report Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.08882","title":"Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals","created":"2026-02-09","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":"2604.08293","title":"CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2608.07494","title":"How to Ask the AI: A User Perspective Survey for Large Language Model Prompting","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.09558","title":"Training-Free Universal Approximation by Prompting Random Transformers","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2312.12598","title":"A Case Study on Test Case Construction with Large Language Models: Unveiling Practical Insights and Challenges","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2404.08821","title":"Constrained C-Test Generation via Mixed-Integer Programming","created":"2024-04-12","cited_by_count":0,"area":null}],"next_cursor":"100"}