{"total":134,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125,"area":null},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103,"area":null},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2309.11674","title":"A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models","created":"2023-09-20","cited_by_count":89,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2310.15080","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","created":"2023-10-23","cited_by_count":65,"area":null},{"id":"2402.02370","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","created":"2024-02-04","cited_by_count":65,"area":null},{"id":"2309.13567","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","created":"2023-09-24","cited_by_count":63,"area":null},{"id":"2501.10326","title":"Large language models for automated scholarly paper review: A survey","created":"2025-01-17","cited_by_count":61,"area":null},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57,"area":null},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2309.02033","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","created":"2023-09-05","cited_by_count":52,"area":null},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2209.14500","title":"Bidirectional Language Models Are Also Few-shot Learners","created":"2022-09-29","cited_by_count":48,"area":null},{"id":"2406.05688","title":"Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions","created":"2024-06-09","cited_by_count":46,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"area":null},{"id":"2208.04347","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","created":"2022-08-08","cited_by_count":43,"area":null},{"id":"2210.15303","title":"Can language models handle recursively nested grammatical structures? A case study on comparing models and humans","created":"2022-10-27","cited_by_count":41,"area":null},{"id":"2210.17041","title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","created":"2022-10-31","cited_by_count":37,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2212.10315","title":"HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28,"area":null},{"id":"2406.15477","title":"CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2211.08473","title":"On the Compositional Generalization Gap of In-Context Learning","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2402.06894","title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","created":"2024-02-10","cited_by_count":22,"area":null},{"id":"2210.12152","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2406.12529","title":"LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2404.11122","title":"Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification","created":"2024-04-17","cited_by_count":18,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"area":null},{"id":"2310.05136","title":"InstructDET: Diversifying Referring Object Detection with Generalized Instructions","created":"2023-10-08","cited_by_count":16,"area":null},{"id":"2205.11726","title":"On the Role of Bidirectionality in Language Model Pre-Training","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2305.16651","title":"TADA: Task-Agnostic Dialect Adapters for English","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2507.21160","title":"Handling Out-of-Distribution Data: A Survey","created":"2025-07-25","cited_by_count":14,"area":null},{"id":"2409.00342","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation","created":"2024-08-31","cited_by_count":13,"area":null},{"id":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2401.12789","title":"Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study","created":"2024-01-23","cited_by_count":12,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2506.10766","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2306.00168","title":"Measuring the Robustness of NLP Models to Domain Shifts","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2306.16322","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2401.07031","title":"Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models","created":"2024-01-13","cited_by_count":10,"area":null},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2505.13499","title":"Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2405.05455","title":"Automated Program Repair: Emerging trends pose and expose problems for benchmarks","created":"2024-05-08","cited_by_count":7,"area":null},{"id":"2407.00935","title":"Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2304.06875","title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2402.12170","title":"Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2403.00236","title":"Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance","created":"2024-03-01","cited_by_count":6,"area":null},{"id":"2212.10929","title":"SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2402.08250","title":"A survey of recent methods for addressing AI fairness and bias in biomedicine","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2403.06086","title":"Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach","created":"2024-03-10","cited_by_count":5,"area":null},{"id":"2410.01600","title":"ENTP: Encoder-only Next Token Prediction","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2210.14593","title":"Scaling Laws Beyond Backpropagation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2305.14243","title":"Training Transitive and Commutative Multimodal Transformers with LoReTTa","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2403.01570","title":"Small Models are LLM Knowledge Triggers on Medical Tabular Prediction","created":"2024-03-03","cited_by_count":4,"area":null},{"id":"2406.12382","title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2409.00571","title":"Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2504.12721","title":"TimeCapsule: Solving the Jigsaw Puzzle of Long-Term Time Series Forecasting with Compressed Predictive Representations","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2505.06633","title":"Attention Is Not All You Need: The Importance of Feedforward Networks in Transformer Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2510.26622","title":"Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2601.02031","title":"Output Embedding Centering for Stable LLM Pretraining","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2210.13432","title":"Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2406.00318","title":"KGLink: A column type annotation method that combines knowledge graph and pre-trained language model","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2412.04503","title":"A Primer on Large Language Models and their Limitations","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2509.19696","title":"Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","cited_by_count":2,"area":null}],"next_cursor":"100"}