{"list":"other","total":53,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"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":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2312.11805","title":"Gemini: A Family of Highly Capable Multimodal Models","created":"2023-12-19","cited_by_count":872},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2402.13228","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","created":"2024-02-20","cited_by_count":241},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143},{"id":"2210.06726","title":"Explanations from Large Language Models Make Small Reasoners Better","created":"2022-10-13","cited_by_count":124},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108},{"id":"2402.10963","title":"GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements","created":"2024-02-13","cited_by_count":103},{"id":"2311.09724","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","created":"2023-11-16","cited_by_count":85},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70},{"id":"2309.15028","title":"Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding","created":"2023-09-26","cited_by_count":60},{"id":"2402.02658","title":"Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision","created":"2024-02-05","cited_by_count":52},{"id":"2402.00658","title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","created":"2024-02-01","cited_by_count":49},{"id":"2205.14318","title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","created":"2022-05-28","cited_by_count":38},{"id":"2303.03628","title":"CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification","created":"2023-03-07","cited_by_count":11}],"next_cursor":null}