{"list":"other","total":63,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2004.07347","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","created":"2020-04-15","cited_by_count":264},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2402.05044","title":"SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models","created":"2024-02-07","cited_by_count":228},{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112},{"id":"2401.08671","title":"DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference","created":"2024-01-09","cited_by_count":106},{"id":"2305.17306","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","created":"2023-05-26","cited_by_count":102},{"id":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86},{"id":"2407.17436","title":"AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies","created":"2024-07-11","cited_by_count":74},{"id":"2401.09646","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","created":"2024-01-17","cited_by_count":47},{"id":"1905.02158","title":"Parsl: Pervasive Parallel Programming in Python","created":"2019-05-06","cited_by_count":36},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34},{"id":"2405.00972","title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","created":"2024-05-02","cited_by_count":33},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28},{"id":"2403.04307","title":"HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild","created":"2024-03-07","cited_by_count":27},{"id":"2412.14642","title":"Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation","created":"2024-12-19","cited_by_count":25},{"id":"2406.12950","title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","created":"2024-06-18","cited_by_count":24},{"id":"2403.08192","title":"MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension","created":"2024-03-13","cited_by_count":22},{"id":"2407.11435","title":"Genomic Language Models: Opportunities and Challenges","created":"2024-07-16","cited_by_count":20},{"id":"2406.06357","title":"MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows","created":"2024-06-10","cited_by_count":19},{"id":"2406.10707","title":"DataStates-LLM: Lazy Asynchronous Checkpointing for Large Language Models","created":"2024-06-15","cited_by_count":16},{"id":"2405.05548","title":"Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis","created":"2024-05-09","cited_by_count":12},{"id":"2406.02524","title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","created":"2024-06-04","cited_by_count":10},{"id":"2412.10477","title":"Benchmarking large language models for materials synthesis: the case of atomic layer deposition","created":"2024-12-13","cited_by_count":8},{"id":"2407.11194","title":"AstroMLab 1: Who Wins Astronomy Jeopardy!?","created":"2024-07-15","cited_by_count":7},{"id":"2311.17107","title":"ClimateX: Do LLMs Accurately Assess Human Expert Confidence in Climate Statements?","created":"2023-11-28","cited_by_count":3},{"id":"2401.00290","title":"Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks","created":"2023-12-30","cited_by_count":3},{"id":"2408.03732","title":"Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks","created":"2024-08-07","cited_by_count":3},{"id":"2410.06932","title":"Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models","created":"2024-10-09","cited_by_count":2}],"next_cursor":null}