{"total":123,"rows":[{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843,"area":"inference"},{"id":"2405.07940","title":"RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors","created":"2024-05-13","cited_by_count":163,"area":null},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2402.06925","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","created":"2024-02-10","cited_by_count":114,"area":null},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113,"area":"wm"},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"area":null},{"id":"2312.03748","title":"Applying Large Language Models and Chain-of-Thought for Automatic Scoring","created":"2023-11-30","cited_by_count":69,"area":"lr"},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58,"area":null},{"id":"2408.17355","title":"Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling","created":"2024-08-30","cited_by_count":52,"area":null},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51,"area":null},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2403.09919","title":"Recurrent Drafter for Fast Speculative Decoding in Large Language Models","created":"2024-03-14","cited_by_count":37,"area":"inference"},{"id":"2212.14578","title":"MAUVE Scores for Generative Models: Theory and Practice","created":"2022-12-30","cited_by_count":36,"area":null},{"id":"2310.13659","title":"Benchmarking and Improving Text-to-SQL Generation under Ambiguity","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2311.14919","title":"Faster Minimum Bayes Risk Decoding with Confidence-based Pruning","created":"2023-11-25","cited_by_count":34,"area":null},{"id":"2305.02633","title":"Conformal Nucleus Sampling","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2309.10966","title":"MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods","created":"2023-09-19","cited_by_count":33,"area":null},{"id":"2310.01693","title":"Closing the Curious Case of Neural Text Degeneration","created":"2023-10-02","cited_by_count":32,"area":null},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2402.04251","title":"Linear-time Minimum Bayes Risk Decoding with Reference Aggregation","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2402.18223","title":"Improving Open-Ended Text Generation via Adaptive Decoding","created":"2024-02-28","cited_by_count":21,"area":null},{"id":"2303.04729","title":"Stealing the Decoding Algorithms of Language Models","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2408.13586","title":"Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation","created":"2024-08-24","cited_by_count":19,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2305.12675","title":"A Frustratingly Simple Decoding Method for Neural Text Generation","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2305.16958","title":"MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies","created":"2023-05-26","cited_by_count":16,"area":null},{"id":"2401.02749","title":"Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding","created":"2024-01-05","cited_by_count":15,"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":"2310.14971","title":"Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation","created":"2023-10-23","cited_by_count":13,"area":null},{"id":"2401.06688","title":"Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation","created":"2024-01-12","cited_by_count":13,"area":null},{"id":"2406.02832","title":"Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2311.05263","title":"Model-Based Minimum Bayes Risk Decoding for Text Generation","created":"2023-11-09","cited_by_count":11,"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":"2406.07735","title":"REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2305.13477","title":"Look-back Decoding for Open-Ended Text Generation","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2408.06537","title":"Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data","created":"2024-08-13","cited_by_count":10,"area":null},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2506.13681","title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2507.02974","title":"InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy","created":"2025-06-30","cited_by_count":10,"area":"rag"},{"id":"2508.20757","title":"GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation","created":"2025-08-28","cited_by_count":10,"area":null},{"id":"2310.06707","title":"Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2407.10456","title":"Don't Throw Away Data: Better Sequence Knowledge Distillation","created":"2024-07-15","cited_by_count":9,"area":"distill"},{"id":"2410.15021","title":"Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding","created":"2024-10-19","cited_by_count":9,"area":null},{"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":"2506.23601","title":"Semantic-guided Diverse Decoding for Large Language Model","created":"2025-06-30","cited_by_count":9,"area":null},{"id":"2509.02510","title":"Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation","created":"2025-09-02","cited_by_count":9,"area":null},{"id":"2509.17570","title":"Asking a Language Model for Diverse Responses","created":"2025-09-22","cited_by_count":9,"area":"lr"},{"id":"2604.11012","title":"Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics","created":"2026-04-13","cited_by_count":9,"area":null},{"id":"2302.06784","title":"The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2502.00602","title":"Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing","created":"2025-02-02","cited_by_count":8,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2310.05628","title":"Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2501.17295","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","created":"2025-01-28","cited_by_count":6,"area":"alignment"},{"id":"2410.10810","title":"Local and Global Decoding in Text Generation","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2509.23234","title":"p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2510.05987","title":"Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2411.06251","title":"Quasi-random Multi-Sample Inference for Large Language Models","created":"2024-11-09","cited_by_count":4,"area":null},{"id":"2502.11115","title":"Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2502.18890","title":"TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2503.21929","title":"Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2508.06094","title":"ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline","created":"2025-08-08","cited_by_count":4,"area":null},{"id":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2604.04987","title":"Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling","created":"2026-04-05","cited_by_count":4,"area":"inference"},{"id":"2606.27359","title":"When are likely answers right? On Sequence Probability and Correctness in LLMs","created":"2026-06-25","cited_by_count":4,"area":null},{"id":"2409.07615","title":"MOSAIC: Multiple Observers Spotting AI Content","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2410.09675","title":"COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2502.12685","title":"Theoretical Guarantees for Minimum Bayes Risk Decoding","created":"2025-02-18","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":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.10346","title":"Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.18482","title":"The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2307.12996","title":"Extracting Molecular Properties from Natural Language with Multimodal Contrastive Learning","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2403.05788","title":"On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization","created":"2024-03-09","cited_by_count":2,"area":null},{"id":"2404.00752","title":"On the True Distribution Approximation of Minimum Bayes-Risk Decoding","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2411.09694","title":"A Bayesian Optimization Approach to Machine Translation Reranking","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2412.04205","title":"A Context-aware Framework for Translation-mediated Conversations","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2507.18338","title":"Uncertainty Quantification for Evaluating Machine Translation Bias","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2510.19471","title":"Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2604.27674","title":"One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2502.11723","title":"Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2508.13580","title":"A Comparative Study of Decoding Strategies in Medical Text Generation","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.09942","title":"Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding","created":"2025-10-11","cited_by_count":1,"area":"inference"},{"id":"2601.01714","title":"Entropy-Aligned Decoding of LMs for Better Writing and Reasoning","created":"2026-01-05","cited_by_count":1,"area":"lr"},{"id":"2601.22536","title":"Decoding in Geometry: Alleviating Embedding-Space Crowding for Complex Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.14567","title":"Top-b: Entropic Regulation of Relative Probability Bands in Autoregressive Language Processes","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2604.18697","title":"Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs","created":"2026-04-20","cited_by_count":1,"area":"safety"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.10407","title":"Identified-Set Geometry of Distributional Model Extraction under Top-$K$ Censored API Access","created":"2026-05-11","cited_by_count":1,"area":"distill"},{"id":"2605.22579","title":"Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.13982","title":"Adaptive Nucleus Truncation for Long-Form Reasoning","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.22511","title":"Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2609.01043","title":"From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion","created":"2026-09-01","cited_by_count":1,"area":"diffusion"},{"id":"2609.13520","title":"From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models","created":"2026-09-11","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}