{"total":90,"rows":[{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318,"area":"rag"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"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":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135,"area":"alignment"},{"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":"2310.11877","title":"The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models","created":"2023-10-18","cited_by_count":55,"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":"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":"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":"2407.00211","title":"Detection and Measurement of Syntactic Templates in Generated Text","created":"2024-06-28","cited_by_count":44,"area":null},{"id":"2404.03502","title":"AI and the Problem of Knowledge Collapse","created":"2024-04-04","cited_by_count":34,"area":null},{"id":"2401.14016","title":"Towards Uncertainty-Aware Language Agent","created":"2024-01-25","cited_by_count":32,"area":"agents"},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2410.06097","title":"Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation","created":"2024-10-08","cited_by_count":26,"area":null},{"id":"2404.03746","title":"GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2402.05864","title":"Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs","created":"2024-02-08","cited_by_count":22,"area":"safety"},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","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":"2203.17217","title":"On the probability-quality paradox in language generation","created":"2022-03-31","cited_by_count":16,"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":"2410.12138","title":"Preference Optimization with Multi-Sample Comparisons","created":"2024-10-16","cited_by_count":16,"area":"diffusion"},{"id":"2510.22391","title":"Top-Down Semantic Refinement for Image Captioning","created":"2025-10-25","cited_by_count":16,"area":"mllm"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","cited_by_count":12,"area":"alignment"},{"id":"2406.07850","title":"Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation","created":"2024-06-12","cited_by_count":10,"area":null},{"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":"2406.10773","title":"Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articles","created":"2024-06-16","cited_by_count":9,"area":null},{"id":"2410.18653","title":"Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2508.03098","title":"Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation","created":"2025-08-05","cited_by_count":8,"area":"rag"},{"id":"2403.20252","title":"Using LLMs to Model the Beliefs and Preferences of Targeted Populations","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2410.03968","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2412.09727","title":"A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management","created":"2024-12-12","cited_by_count":6,"area":null},{"id":"2210.07228","title":"Language Model Decoding as Likelihood-Utility Alignment","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2405.17658","title":"Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2407.03951","title":"Uncertainty-Guided Likelihood Tree Search","created":"2024-07-04","cited_by_count":4,"area":"lr"},{"id":"2410.12222","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","created":"2024-10-16","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":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2506.15846","title":"Finance Language Model Evaluation (FLaME)","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2511.06259","title":"Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra","created":"2025-11-09","cited_by_count":4,"area":null},{"id":"2210.10817","title":"A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2305.15344","title":"Learning Answer Generation using Supervision from Automatic Question Answering Evaluators","created":"2023-05-24","cited_by_count":3,"area":"rag"},{"id":"2309.04858","title":"Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2401.13594","title":"Graph Guided Question Answer Generation for Procedural Question-Answering","created":"2024-01-24","cited_by_count":3,"area":null},{"id":"2507.21086","title":"Multi-Amateur Contrastive Decoding for Text Generation","created":"2025-06-22","cited_by_count":3,"area":null},{"id":"2602.04033","title":"On the Credibility of Evaluating LLMs using Survey Questions","created":"2026-02-03","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":"2311.14685","title":"Comprehensive Assessment of Toxicity in ChatGPT","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2503.13923","title":"ConSCompF: Consistency-focused Similarity Comparison Framework for Generative Large Language Models","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2503.20429","title":"Latent Beam Diffusion Models for Generating Visual Sequences","created":"2025-03-26","cited_by_count":2,"area":"diffusion"},{"id":"2506.17171","title":"Deep generative models as the probability transformation functions","created":"2025-06-20","cited_by_count":2,"area":"diffusion"},{"id":"2510.02719","title":"TravelBench : Exploring LLM Performance in Low-Resource Domains","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2602.01685","title":"Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2311.10943","title":"Partially Randomizing Transformer Weights for Dialogue Response Diversity","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2402.11710","title":"A Note on Bias to Complete","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2409.19001","title":"Pay Attention to What Matters","created":"2024-09-19","cited_by_count":1,"area":null},{"id":"2501.06370","title":"Towards a Probabilistic Framework for Analyzing and Improving LLM-Enabled Software","created":"2025-01-10","cited_by_count":1,"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":"2505.11183","title":"On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms","created":"2025-05-16","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":"2508.15371","title":"Confidence-Modulated Speculative Decoding for Large Language Models","created":"2025-08-21","cited_by_count":1,"area":"inference"},{"id":"2512.04419","title":"Solving LLM Repetition Problem in Production: A Comprehensive Study of Multiple Solutions","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2605.22579","title":"Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.24850","title":"Repeated Sequences Reveal Gaps between Large Language Models and Natural Language","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2608.05448","title":"DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding","created":"2026-08-05","cited_by_count":1,"area":"inference"},{"id":"2210.13829","title":"IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2406.10203","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","created":"2024-06-14","cited_by_count":0,"area":"alignment"},{"id":"2411.19038","title":"DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2501.19337","title":"Token-Level Entropy Reveals Demographic Disparities in Large Language Models","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2505.16418","title":"Exploring the Relationship Between Diversity and Quality in Ad Text Generation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2506.05950","title":"Elementary Math Word Problem Generation using Large Language Models","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2507.21568","title":"Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages","created":"2025-07-29","cited_by_count":0,"area":"distill"},{"id":"2509.01308","title":"GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models","created":"2025-09-01","cited_by_count":0,"area":"lr"},{"id":"2603.14891","title":"Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.09147","title":"From Traditional Taggers to LLMs: A Comparative Study of POS Tagging for Medieval Romance Languages","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.15943","title":"Graphical-Probabilistic Modeling of Generative Flows in LLM-Native Software Systems","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.20714","title":"A Generalized Formalism of Auto-Regressive Decoding for Speech Processing","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2608.03233","title":"On the Diversity of Analogy Making in Large Language Models","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.14797","title":"Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.22758","title":"XTC: Head-Aware Sampling by Excluding Top Choices","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.22761","title":"Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.34509","title":"Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.18820","title":"Read the Room Before Your Model Generates","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}