{"total":93,"rows":[{"id":"2405.20132","title":"LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics","created":"2024-05-30","cited_by_count":97,"area":null},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2501.00273","title":"Echoes in AI: Quantifying lack of plot diversity in LLM outputs","created":"2024-12-31","cited_by_count":48,"area":null},{"id":"2506.07295","title":"Exploring the Impact of Temperature on Large Language Models:Hot or Cold?","created":"2025-06-08","cited_by_count":40,"area":null},{"id":"2504.15485","title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","created":"2025-04-21","cited_by_count":38,"area":"lr"},{"id":"2412.01778","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2024-12-02","cited_by_count":37,"area":"agents"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2501.10604","title":"When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis","created":"2025-01-17","cited_by_count":21,"area":"mllm"},{"id":"2409.11547","title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2502.07508","title":"Enhance-A-Video: Better Generated Video for Free","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2410.21359","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games","created":"2024-10-28","cited_by_count":9,"area":"lr"},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2408.08841","title":"FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats","created":"2024-08-16","cited_by_count":8,"area":"lr"},{"id":"2502.03678","title":"Reflection-Window Decoding: Text Generation with Selective Refinement","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2503.19257","title":"SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings","created":"2025-03-25","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2502.20933","title":"MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models","created":"2025-02-28","cited_by_count":7,"area":null},{"id":"2503.02582","title":"Playing games with Large language models: Randomness and strategy","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","cited_by_count":7,"area":"synth"},{"id":"2505.17139","title":"EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2507.05123","title":"An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2508.09654","title":"Improving Diversity in Language Models: When Temperature Fails, Change the Loss","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2412.13422","title":"Generating Diverse Hypotheses for Inductive Reasoning","created":"2024-12-18","cited_by_count":6,"area":"lr"},{"id":"2502.14930","title":"RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practice","created":"2025-02-20","cited_by_count":6,"area":"rag"},{"id":"2504.12320","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2501.16356","title":"Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations","created":"2025-01-20","cited_by_count":5,"area":"agents"},{"id":"2602.04184","title":"Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action Models","created":"2026-02-04","cited_by_count":5,"area":"vla"},{"id":"2407.03007","title":"What Affects the Stability of Tool Learning? An Empirical Study on the Robustness of Tool Learning Frameworks","created":"2024-07-03","cited_by_count":4,"area":"agents"},{"id":"2411.10599","title":"Generating Energy-efficient code with LLMs","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2412.16177","title":"Mining Math Conjectures from LLMs: A Pruning Approach","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2501.05032","title":"Enhancing Human-Like Responses in Large Language Models","created":"2025-01-09","cited_by_count":4,"area":null},{"id":"2502.12185","title":"Large Language Models for Extrapolative Modeling of Manufacturing Processes","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2502.20689","title":"WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosis","created":"2025-02-28","cited_by_count":4,"area":"agents"},{"id":"2503.00847","title":"Argument Summarization and its Evaluation in the Era of Large Language Models","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2508.16678","title":"Cognitive Agents Powered by Large Language Models for Agile Software Project Management","created":"2025-08-21","cited_by_count":4,"area":"agents"},{"id":"2601.11227","title":"Language of Thought Shapes Output Diversity in Large Language Models","created":"2026-01-16","cited_by_count":4,"area":"lr"},{"id":"2410.05045","title":"Can LLMs plan paths with extra hints from solvers?","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.05292","title":"CaLMFlow: Volterra Flow Matching using Causal Language Models","created":"2024-10-03","cited_by_count":3,"area":"diffusion"},{"id":"2502.14037","title":"DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2507.13874","title":"Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2509.14405","title":"Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings","created":"2025-09-17","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":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2408.02964","title":"Accuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2501.05601","title":"Exploring Large Language Models for Translating Romanian Computational Problems into English","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2502.03916","title":"Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Software","created":"2025-02-06","cited_by_count":2,"area":"rag"},{"id":"2504.06600","title":"Automated Business Process Analysis: An LLM-Based Approach to Value Assessment","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2505.20672","title":"GIFARC: Synthetic Dataset for Leveraging Human-Intuitive Analogies to Elevate AI Reasoning","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2507.21831","title":"Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.21024","title":"An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs","created":"2025-08-28","cited_by_count":2,"area":"rag"},{"id":"2602.14286","title":"Online LLM watermark detection via e-processes","created":"2026-02-15","cited_by_count":2,"area":"safety"},{"id":"2603.19519","title":"Inducing Sustained Creativity and Diversity in Large Language Models","created":"2026-03-19","cited_by_count":2,"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":"2607.01433","title":"CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2412.16412","title":"InfoTech Assistant: A Multimodal Conversational Agent for InfoTechnology Web Portal Queries","created":"2024-12-21","cited_by_count":1,"area":"agents"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2505.04497","title":"Defining and Quantifying Creative Behavior in Popular Image Generators","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2508.03342","title":"From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2602.14862","title":"The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling","created":"2026-02-16","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":"2603.20381","title":"The production of meaning in the processing of natural language","created":"2026-03-20","cited_by_count":1,"area":"mechinterp"},{"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":"2604.13242","title":"On the Creativity of AI Agents","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.16757","title":"Expressing Social Emotions: Misalignment Between LLMs and Human Cultural Emotion Norms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2605.27268","title":"Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2607.18310","title":"Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2409.02291","title":"Initial Development and Evaluation of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) System","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2409.09054","title":"Evaluating the Performance of Large Language Models in Competitive Programming: A Multi-Year, Multi-Grade Analysis","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2501.12033","title":"Harnessing Generative Pre-Trained Transformer for Datacenter Packet Trace Generation","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2502.18205","title":"Grandes modelos de lenguaje: de la predicci\\'on de palabras a la comprensi\\'on?","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2506.01367","title":"MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations","created":"2025-06-02","cited_by_count":0,"area":"agents"},{"id":"2506.21031","title":"Large Language Models Acing Chartered Accountancy","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.03726","title":"Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models","created":"2025-07-04","cited_by_count":0,"area":"agents"},{"id":"2508.10011","title":"Evaluation of GPT-based large language generative AI models as study aids for the national licensure examination for registered dietitians in Japan","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2511.09571","title":"General Intelligence-based Fragmentation (GIF): A framework for peak-labeled spectra simulation","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.09548","title":"Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.00875","title":"IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01811","title":"\"I've Seen How This Goes\": Characterizing Diversity via Progressive Conditional Surprise","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.01152","title":"AGC-Bench: Measuring Artificial General Creativity","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.11783","title":"How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?","created":"2026-07-13","cited_by_count":0,"area":"rag"},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.20791","title":"Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.04835","title":"On Epistemic Diversity in Large Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.32196","title":"The Judge Is Not Its Twin: Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.09824","title":"Homogenization in Multi-Agent Systems","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11539","title":"Design Creativity Bench: Measuring creativity in LLM-Generated UI","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14980","title":"Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}