{"list":"other","total":58,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"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":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2211.09110","title":"Holistic Evaluation of Language Models","created":"2022-11-16","cited_by_count":131},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2403.02333","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","created":"2024-03-04","cited_by_count":58},{"id":"2402.14865","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","created":"2024-02-21","cited_by_count":54},{"id":"2309.10677","title":"Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation","created":"2023-09-19","cited_by_count":48},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36},{"id":"2308.00304","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","created":"2023-08-01","cited_by_count":33},{"id":"2310.15147","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","created":"2023-10-23","cited_by_count":18},{"id":"2402.13125","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","created":"2024-02-20","cited_by_count":14},{"id":"2312.15746","title":"Large Language Models are Not Stable Recommender Systems","created":"2023-12-25","cited_by_count":13}],"next_cursor":null}