{"total":21,"rows":[{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2412.10271","title":"Benchmarking Linguistic Diversity of Large Language Models","created":"2024-12-13","cited_by_count":38,"area":null},{"id":"2410.04197","title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"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":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2501.04927","title":"Investigating Numerical Translation with Large Language Models","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2506.21783","title":"Evaluating List Construction and Temporal Understanding capabilities of Large Language Models","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2602.08660","title":"Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.28022","title":"Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2509.23811","title":"AnveshanaAI: A Multimodal Platform for Adaptive AI/ML Education through Automated Question Generation and Interactive Assessment","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2602.09340","title":"Measuring Dataset Diversity from a Geometric Perspective","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2606.12790","title":"GENIE: A Fine-Grained Measure for Novelty","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.04563","title":"Fidelity-Diversity Metrics for Text","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.24228","title":"Evaluating Multiple LLM Generations with Validated Task Coverage","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.02275","title":"Do Large Language Models Capture the Diversity in their Training Data?","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.26527","title":"A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.06513","title":"SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14031","title":"PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}