{"list":"other","total":70,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123},{"id":"2402.06925","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","created":"2024-02-10","cited_by_count":114},{"id":"2310.07177","title":"Online Speculative Decoding","created":"2023-10-11","cited_by_count":113},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111},{"id":"2403.07816","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","created":"2024-03-12","cited_by_count":109},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105},{"id":"2004.10450","title":"Trading Off Diversity and Quality in Natural Language Generation","created":"2020-04-22","cited_by_count":96},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90},{"id":"2408.11850","title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","created":"2024-08-13","cited_by_count":85},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74},{"id":"2406.17276","title":"OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure","created":"2024-06-25","cited_by_count":67},{"id":"2408.12599","title":"Controllable Text Generation for Large Language Models: A Survey","created":"2024-08-22","cited_by_count":57},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49},{"id":"2405.02750","title":"Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding","created":"2024-05-04","cited_by_count":49},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41},{"id":"2410.10814","title":"Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free","created":"2024-10-14","cited_by_count":37},{"id":"2212.14578","title":"MAUVE Scores for Generative Models: Theory and Practice","created":"2022-12-30","cited_by_count":36},{"id":"2001.08785","title":"Semi-Autoregressive Training Improves Mask-Predict Decoding","created":"2020-01-23","cited_by_count":33},{"id":"2405.04304","title":"Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models","created":"2024-05-07","cited_by_count":31},{"id":"2009.07243","title":"A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation","created":"2020-09-15","cited_by_count":28},{"id":"2311.08380","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","created":"2023-11-14","cited_by_count":28},{"id":"2402.14160","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","created":"2024-02-21","cited_by_count":27},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25},{"id":"2305.12018","title":"BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases","created":"2023-05-19","cited_by_count":24},{"id":"2401.06761","title":"APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding","created":"2024-01-12","cited_by_count":24},{"id":"2404.03865","title":"FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping","created":"2024-04-05","cited_by_count":23},{"id":"2403.00858","title":"Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs","created":"2024-02-29","cited_by_count":22},{"id":"2205.14690","title":"CoNT: Contrastive Neural Text Generation","created":"2022-05-29","cited_by_count":21},{"id":"2210.15458","title":"Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models","created":"2022-10-18","cited_by_count":19},{"id":"2404.02852","title":"Toward Inference-optimal Mixture-of-Expert Large Language Models","created":"2024-04-03","cited_by_count":19},{"id":"2406.17519","title":"Entropy-Based Decoding for Retrieval-Augmented Large Language Models","created":"2024-06-25","cited_by_count":19},{"id":"2402.14874","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","created":"2024-02-21","cited_by_count":16},{"id":"2412.00061","title":"Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration","created":"2024-11-25","cited_by_count":15},{"id":"2012.15416","title":"Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation","created":"2020-12-31","cited_by_count":12},{"id":"2402.06700","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","created":"2024-02-09","cited_by_count":12},{"id":"2402.00943","title":"Approximate Nearest Neighbor Search with Window Filters","created":"2024-02-01","cited_by_count":11},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11},{"id":"2411.01610","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","created":"2024-11-03","cited_by_count":11},{"id":"2406.07368","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","created":"2024-06-11","cited_by_count":9},{"id":"2407.12021","title":"Adaptive Draft-Verification for Efficient Large Language Model Decoding","created":"2024-06-27","cited_by_count":9},{"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},{"id":"2404.16322","title":"Effective and General Distance Computation for Approximate Nearest Neighbor Search","created":"2024-04-25","cited_by_count":8},{"id":"2405.18906","title":"Language Generation with Strictly Proper Scoring Rules","created":"2024-05-29","cited_by_count":8},{"id":"2211.11924","title":"Best-$k$ Search Algorithm for Neural Text Generation","created":"2022-11-22","cited_by_count":6},{"id":"2408.08146","title":"KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning","created":"2024-08-15","cited_by_count":6},{"id":"2310.11976","title":"InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generation","created":"2023-10-18","cited_by_count":5},{"id":"2409.16560","title":"Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference","created":"2024-09-25","cited_by_count":5},{"id":"2305.12330","title":"Task-agnostic Distillation of Encoder-Decoder Language Models","created":"2023-05-21","cited_by_count":4},{"id":"2405.00888","title":"DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling","created":"2024-05-01","cited_by_count":4},{"id":"2407.03951","title":"Uncertainty-Guided Likelihood Tree Search","created":"2024-07-04","cited_by_count":4},{"id":"2404.12022","title":"Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration","created":"2024-04-18","cited_by_count":3},{"id":"2405.15208","title":"Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs","created":"2024-05-24","cited_by_count":2}],"next_cursor":null}