{"total":81,"rows":[{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232,"area":null},{"id":"2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","created":"2023-09-11","cited_by_count":192,"area":null},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100,"area":null},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2405.20253","title":"Evaluating Large Language Model Biases in Persona-Steered Generation","created":"2024-05-30","cited_by_count":78,"area":null},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58,"area":null},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"area":null},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50,"area":null},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2505.18949","title":"The Price of Format: Diversity Collapse in LLMs","created":"2025-05-25","cited_by_count":43,"area":null},{"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":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2204.00862","title":"CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation","created":"2022-04-02","cited_by_count":29,"area":null},{"id":"2205.01497","title":"Semantic Diversity in Dialogue with Natural Language Inference","created":"2022-05-03","cited_by_count":29,"area":null},{"id":"2505.15229","title":"Multilingual Prompting for Improving LLM Generation Diversity","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22,"area":null},{"id":"2410.15956","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2311.16054","title":"Metric Space Magnitude for Evaluating the Diversity of Latent Representations","created":"2023-11-27","cited_by_count":17,"area":null},{"id":"2406.15267","title":"Evaluating Diversity in Automatic Poetry Generation","created":"2024-06-21","cited_by_count":17,"area":null},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2312.10355","title":"CoAScore: Chain-of-Aspects Prompting for NLG Evaluation","created":"2023-12-16","cited_by_count":14,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2401.05054","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","created":"2024-01-10","cited_by_count":11,"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":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2208.03438","title":"DeepGen: Diverse Search Ad Generation and Real-Time Customization","created":"2022-08-06","cited_by_count":10,"area":null},{"id":"2306.12719","title":"Natural Language Generation for Advertising: A Survey","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2506.18082","title":"Statistical Multicriteria Evaluation of LLM-Generated Text","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2506.21742","title":"VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2502.11671","title":"Diversity-oriented Data Augmentation with Large Language Models","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2102.01263","title":"MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations","created":"2021-02-02","cited_by_count":6,"area":null},{"id":"2509.19163","title":"Measuring AI \"Slop\" in Text","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2205.02035","title":"Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking","created":"2022-05-04","cited_by_count":5,"area":null},{"id":"2206.00564","title":"Exploring Diversity in Back Translation for Low-Resource Machine Translation","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2306.07554","title":"HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2409.03021","title":"CLUE: Concept-Level Uncertainty Estimation for Large Language Models","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2605.09995","title":"Annotations Mitigate Post-Training Mode Collapse","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2507.20858","title":"A survey of diversity quantification in natural language processing: The why, what, where and how","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2509.16564","title":"MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2405.15067","title":"Promoting Constructive Deliberation: Reframing for Receptiveness","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2502.14037","title":"DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2508.18739","title":"Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2607.12796","title":"The One-Word Census: Answer-Choice Conformity Across 105 Language Models","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2105.03641","title":"Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2301.08145","title":"Music Playlist Title Generation Using Artist Information","created":"2023-01-14","cited_by_count":2,"area":null},{"id":"2305.14815","title":"Machine Reading Comprehension using Case-based Reasoning","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.03726","title":"Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2604.02319","title":"No Single Best Model for Diversity: Learning a Router for Sample Diversity","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2304.02812","title":"Pragmatically Appropriate Diversity for Dialogue Evaluation","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2309.06550","title":"Synthetic Text Generation using Hypergraph Representations","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2311.10943","title":"Partially Randomizing Transformer Weights for Dialogue Response Diversity","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2403.02610","title":"ChatGPT4PCG 2 Competition: Prompt Engineering for Science Birds Level Generation","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2408.00769","title":"Decoding AI and Human Authorship: Nuances Revealed Through NLP and Statistical Analysis","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2505.09062","title":"Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2507.23440","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2509.26160","title":"MGen: Millions of Naturally Occurring Generics in Context","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2605.30150","title":"Anchorless Diversification for Parallel LLM Ideation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.19848","title":"emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.11426","title":"Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2103.11011","title":"Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2408.06186","title":"Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2504.20849","title":"JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2509.17794","title":"Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2602.06049","title":"Recontextualizing Famous Quotes for Brand Slogan Generation","created":"2026-01-12","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":"2604.16258","title":"Characterising LLM-Generated Competency Questions: a Cross-Domain Empirical Study using Open and Closed Models","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.30844","title":"Fine-Tuning Improves Information Conveyance in Language Models","created":"2026-05-29","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":"2608.17731","title":"Evaluating the Diversity of AI-Generated Content with Diversity Profiles","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.16454","title":"Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs","created":"2026-09-15","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":"2609.33936","title":"How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.12998","title":"Evaluating LLM Creativity through Long-Tail Performance","created":"2026-10-09","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}