{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"1707.02633","title":"Controlling Linguistic Style Aspects in Neural Language Generation","created":"2017-07-09","cited_by_count":149},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2310.15141","title":"SpecTr: Fast Speculative Decoding via Optimal Transport","created":"2023-10-23","cited_by_count":129},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85},{"id":"2009.04202","title":"Impact of News on the Commodity Market: Dataset and Results","created":"2020-09-09","cited_by_count":80},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80},{"id":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80},{"id":"2004.12814","title":"Why should we add early exits to neural networks?","created":"2020-04-27","cited_by_count":70},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67},{"id":"2203.06569","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","created":"2022-03-13","cited_by_count":61},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60},{"id":"2006.06936","title":"Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?","created":"2020-06-12","cited_by_count":59},{"id":"1706.00885","title":"IDK Cascades: Fast Deep Learning by Learning not to Overthink","created":"2017-06-03","cited_by_count":48},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46},{"id":"2409.05816","title":"Improving Pretraining Data Using Perplexity Correlations","created":"2024-09-09","cited_by_count":46},{"id":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45},{"id":"2210.05528","title":"Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems","created":"2022-10-11","cited_by_count":44},{"id":"2012.01988","title":"Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models","created":"2020-12-03","cited_by_count":39},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38},{"id":"2409.15518","title":"Eagle: Efficient Training-Free Router for Multi-LLM Inference","created":"2024-09-23","cited_by_count":35},{"id":"2502.02743","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","created":"2025-02-04","cited_by_count":34},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31},{"id":"2308.11601","title":"Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models","created":"2023-08-22","cited_by_count":30},{"id":"2403.19494","title":"Regression with Multi-Expert Deferral","created":"2024-03-28","cited_by_count":29},{"id":"2403.02683","title":"Learning to Defer to a Population: A Meta-Learning Approach","created":"2024-03-05","cited_by_count":27},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20},{"id":"2311.09758","title":"OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking","created":"2023-11-16","cited_by_count":19},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","cited_by_count":15},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15},{"id":"2301.12386","title":"Plugin estimators for selective classification with out-of-distribution detection","created":"2023-01-29","cited_by_count":14},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8},{"id":"2302.14078","title":"Analyzing Populations of Neural Networks via Dynamical Model Embedding","created":"2023-02-27","cited_by_count":7},{"id":"1711.00894","title":"Multi-Mention Learning for Reading Comprehension with Neural Cascades","created":"2017-11-02","cited_by_count":4},{"id":"2308.05035","title":"Expert load matters: operating networks at high accuracy and low manual effort","created":"2023-08-09","cited_by_count":4}],"next_cursor":null}