{"total":187,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998,"area":null},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392,"area":"lr"},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"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":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484,"area":null},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480,"area":"lr"},{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429,"area":"safety"},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401,"area":"alignment"},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"id":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220,"area":"rag"},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"area":"moe"},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204,"area":null},{"id":"2305.05065","title":"Recommender Systems with Generative Retrieval","created":"2023-05-08","cited_by_count":198,"area":null},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197,"area":"agents"},{"id":"2406.03679","title":"On the Effects of Data Scale on UI Control Agents","created":"2024-06-06","cited_by_count":194,"area":"agents"},{"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":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157,"area":"alignment"},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150,"area":"moe"},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141,"area":"diffusion"},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96,"area":null},{"id":"2410.03983","title":"MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task","created":"2024-10-04","cited_by_count":93,"area":null},{"id":"2302.01398","title":"The unreasonable effectiveness of few-shot learning for machine translation","created":"2023-02-02","cited_by_count":91,"area":"lr"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2406.15765","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","created":"2024-06-22","cited_by_count":74,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67,"area":"alignment"},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65,"area":null},{"id":"2209.14290","title":"FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation","created":"2022-09-28","cited_by_count":63,"area":"rag"},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62,"area":null},{"id":"2403.06265","title":"Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance","created":"2024-03-10","cited_by_count":61,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2305.11841","title":"How Does Generative Retrieval Scale to Millions of Passages?","created":"2023-05-19","cited_by_count":48,"area":null},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44,"area":"lr"},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2410.17413","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","created":"2024-10-22","cited_by_count":42,"area":null},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39,"area":null},{"id":"2301.05327","title":"Blind Judgement: Agent-Based Supreme Court Modelling With GPT","created":"2023-01-12","cited_by_count":38,"area":"agents"},{"id":"2501.05435","title":"Neuro-Symbolic AI in 2024: A Systematic Review","created":"2025-01-09","cited_by_count":38,"area":null},{"id":"2205.12209","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2212.09744","title":"DSI++: Updating Transformer Memory with New Documents","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"area":null},{"id":"2212.08153","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","created":"2022-12-15","cited_by_count":31,"area":"rag"},{"id":"2212.10750","title":"PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition","created":"2022-12-21","cited_by_count":29,"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":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2309.16115","title":"Compositional Sculpting of Iterative Generative Processes","created":"2023-09-28","cited_by_count":27,"area":"diffusion"},{"id":"2308.06912","title":"CausalLM is not optimal for in-context learning","created":"2023-08-14","cited_by_count":26,"area":null},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2209.10372","title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","created":"2022-09-21","cited_by_count":19,"area":null},{"id":"2210.15458","title":"Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models","created":"2022-10-18","cited_by_count":19,"area":null},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2305.06324","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","created":"2023-05-10","cited_by_count":19,"area":"moe"},{"id":"2311.04886","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2401.14019","title":"Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI","created":"2024-01-25","cited_by_count":18,"area":null},{"id":"2301.10448","title":"Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute","created":"2023-01-25","cited_by_count":17,"area":"rag"},{"id":"2404.03626","title":"Training LLMs over Neurally Compressed Text","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2405.13565","title":"AI-Assisted Assessment of Coding Practices in Modern Code Review","created":"2024-05-22","cited_by_count":16,"area":null}],"next_cursor":"100"}