{"list":"other","total":53,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"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":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2405.03548","title":"MAmmoTH2: Scaling Instructions from the Web","created":"2024-05-06","cited_by_count":145},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99},{"id":"2312.17120","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","created":"2023-12-28","cited_by_count":67},{"id":"2404.02893","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","created":"2024-04-03","cited_by_count":47},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30},{"id":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27},{"id":"2206.06315","title":"JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding","created":"2022-06-13","cited_by_count":15},{"id":"2402.12219","title":"Reformatted Alignment","created":"2024-02-19","cited_by_count":15}],"next_cursor":null}