{"list":"other","total":100,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"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":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"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":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231},{"id":"2211.15841","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","created":"2022-11-29","cited_by_count":209},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"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":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102},{"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":"1705.00108","title":"Semi-supervised sequence tagging with bidirectional language models","created":"2017-04-29","cited_by_count":86},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65},{"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":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46},{"id":"2404.09492","title":"Bridging the Gap between Different Vocabularies for LLM Ensemble","created":"2024-04-15","cited_by_count":45},{"id":"2305.14628","title":"Getting MoRE out of Mixture of Language Model Reasoning Experts","created":"2023-05-24","cited_by_count":44},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43},{"id":"2403.00863","title":"LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction","created":"2024-02-29","cited_by_count":39},{"id":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37},{"id":"2401.13979","title":"Routoo: Learning to Route to Large Language Models Effectively","created":"2024-01-25","cited_by_count":34},{"id":"2406.12585","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","created":"2024-06-18","cited_by_count":33},{"id":"2403.19390","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","created":"2024-03-28","cited_by_count":27},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25},{"id":"2005.10084","title":"Context-Aware Learning to Rank with Self-Attention","created":"2020-05-20","cited_by_count":22},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22},{"id":"1704.07156","title":"Semi-supervised Multitask Learning for Sequence Labeling","created":"2017-04-24","cited_by_count":20},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18},{"id":"2406.01013","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","created":"2024-06-03","cited_by_count":14},{"id":"2308.12890","title":"Large Language Models Vote: Prompting for Rare Disease Identification","created":"2023-08-24","cited_by_count":9},{"id":"2403.02799","title":"DPPA: Pruning Method for Large Language Model to Model Merging","created":"2024-03-05","cited_by_count":7},{"id":"2402.16107","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","created":"2024-02-25","cited_by_count":6},{"id":"2405.08373","title":"PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles","created":"2024-05-14","cited_by_count":6},{"id":"2311.08306","title":"On-the-Fly Fusion of Large Language Models and Machine Translation","created":"2023-11-14","cited_by_count":5}],"next_cursor":null}