{"list":"other","total":66,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233},{"id":"2305.15075","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","created":"2023-05-24","cited_by_count":214},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109},{"id":"2303.04132","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction","created":"2023-03-07","cited_by_count":89},{"id":"2305.13735","title":"Aligning Large Language Models through Synthetic Feedback","created":"2023-05-23","cited_by_count":75},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37},{"id":"2402.13514","title":"Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions","created":"2024-02-21","cited_by_count":30},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29},{"id":"2501.11110","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","created":"2025-01-19","cited_by_count":29},{"id":"2406.01006","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","created":"2024-06-03","cited_by_count":27},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27},{"id":"2310.00533","title":"SELF: Self-Evolution with Language Feedback","created":"2023-10-01","cited_by_count":24},{"id":"2411.10914","title":"BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment","created":"2024-11-16","cited_by_count":20},{"id":"2405.04086","title":"Optimizing Language Model's Reasoning Abilities with Weak Supervision","created":"2024-05-07","cited_by_count":15},{"id":"2503.05587","title":"Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","created":"2025-03-07","cited_by_count":10}],"next_cursor":null}