{"list":"other","total":54,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70},{"id":"2305.09246","title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning","created":"2023-05-16","cited_by_count":58},{"id":"2307.06290","title":"Instruction Mining: Instruction Data Selection for Tuning Large Language Models","created":"2023-07-12","cited_by_count":58},{"id":"2009.10855","title":"Controlling Style in Generated Dialogue","created":"2020-09-22","cited_by_count":38},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31},{"id":"2305.10263","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","created":"2023-05-17","cited_by_count":30},{"id":"2409.16430","title":"A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions","created":"2024-09-24","cited_by_count":27},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21},{"id":"2307.08701","title":"AlpaGasus: Training A Better Alpaca with Fewer Data","created":"2023-07-17","cited_by_count":19},{"id":"2212.10466","title":"Controllable Text Generation with Language Constraints","created":"2022-12-20","cited_by_count":18},{"id":"2309.08963","title":"Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?","created":"2023-09-16","cited_by_count":16},{"id":"2305.14987","title":"Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios","created":"2023-05-24","cited_by_count":12},{"id":"2211.07343","title":"Replacing Language Model for Style Transfer","created":"2022-11-14","cited_by_count":3}],"next_cursor":null}