{"list":"other","total":68,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1912.01412","title":"Deep Learning for Symbolic Mathematics","created":"2019-12-02","cited_by_count":270},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2205.00445","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","created":"2022-05-01","cited_by_count":156},{"id":"2312.07559","title":"PaperQA: Retrieval-Augmented Generative Agent for Scientific Research","created":"2023-12-08","cited_by_count":149},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"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":"2402.06852","title":"ChemLLM: A Chemical Large Language Model","created":"2024-02-10","cited_by_count":106},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97},{"id":"2303.13809","title":"Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models","created":"2023-03-24","cited_by_count":87},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2102.02770","title":"A Living Review of Machine Learning for Particle Physics","created":"2021-02-02","cited_by_count":78},{"id":"2305.15074","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","created":"2023-05-24","cited_by_count":77},{"id":"2204.01467","title":"On scientific understanding with artificial intelligence","created":"2022-04-04","cited_by_count":70},{"id":"1901.08644","title":"Ablation Studies in Artificial Neural Networks","created":"2019-01-24","cited_by_count":60},{"id":"2403.01432","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","created":"2024-03-03","cited_by_count":50},{"id":"1807.02876","title":"Machine Learning in High Energy Physics Community White Paper","created":"2018-07-08","cited_by_count":49},{"id":"2401.13537","title":"Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models","created":"2024-01-24","cited_by_count":46},{"id":"2403.05618","title":"OmniJet-$\\alpha$: The first cross-task foundation model for particle physics","created":"2024-03-08","cited_by_count":43},{"id":"2309.06126","title":"AstroLLaMA: Towards Specialized Foundation Models in Astronomy","created":"2023-09-12","cited_by_count":41},{"id":"2402.17403","title":"Sora Generates Videos with Stunning Geometrical Consistency","created":"2024-02-27","cited_by_count":31},{"id":"2402.08565","title":"Artificial Intelligence for Literature Reviews: Opportunities and Challenges","created":"2024-02-13","cited_by_count":30},{"id":"2105.14027","title":"The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider","created":"2021-05-28","cited_by_count":29},{"id":"2411.00446","title":"A Lorentz-Equivariant Transformer for All of the LHC","created":"2024-11-01","cited_by_count":28},{"id":"2402.05929","title":"An Interactive Agent Foundation Model","created":"2024-02-08","cited_by_count":25},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23},{"id":"2405.17044","title":"Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders","created":"2024-05-27","cited_by_count":22},{"id":"2409.12589","title":"Is Tokenization Needed for Masked Particle Modelling?","created":"2024-09-19","cited_by_count":22},{"id":"2401.13536","title":"Finetuning Foundation Models for Joint Analysis Optimization","created":"2024-01-24","cited_by_count":18},{"id":"2405.06107","title":"Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory","created":"2024-05-09","cited_by_count":18},{"id":"2402.17256","title":"Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection","created":"2024-02-27","cited_by_count":14},{"id":"2307.07522","title":"The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence","created":"2023-07-09","cited_by_count":12},{"id":"2402.01889","title":"The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning","created":"2024-02-02","cited_by_count":12},{"id":"2412.07867","title":"Bumblebee: Foundation Model for Particle Physics Discovery","created":"2024-12-10","cited_by_count":12},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11},{"id":"2411.08842","title":"AstroM$^3$: A self-supervised multimodal model for astronomy","created":"2024-11-13","cited_by_count":11},{"id":"2206.00520","title":"Deep Learning Opacity in Scientific Discovery","created":"2022-06-01","cited_by_count":9},{"id":"2304.10327","title":"Towards a Benchmark for Scientific Understanding in Humans and Machines","created":"2023-04-20","cited_by_count":9},{"id":"1905.08628","title":"Constraining the Parameters of High-Dimensional Models with Active Learning","created":"2019-05-19","cited_by_count":8},{"id":"2411.11908","title":"LLM4DS: Evaluating Large Language Models for Data Science Code Generation","created":"2024-11-16","cited_by_count":7},{"id":"2312.02091","title":"Physics simulation capabilities of LLMs","created":"2023-12-04","cited_by_count":6},{"id":"2402.03480","title":"Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision","created":"2024-02-05","cited_by_count":5},{"id":"1604.04315","title":"Moving Beyond the Turing Test with the Allen AI Science Challenge","created":"2016-04-14","cited_by_count":3},{"id":"2006.16082","title":"Measuring Memorization Effect in Word-Level Neural Networks Probing","created":"2020-06-29","cited_by_count":3},{"id":"2401.08525","title":"GATS: Gather-Attend-Scatter","created":"2024-01-16","cited_by_count":3},{"id":"2405.03942","title":"Collaborative Intelligence in Sequential Experiments: A Human-in-the-Loop Framework for Drug Discovery","created":"2024-05-07","cited_by_count":3},{"id":"2409.13447","title":"AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit","created":"2024-09-20","cited_by_count":3},{"id":"2403.03494","title":"Scalable ATLAS pMSSM computational workflows using containerised REANA reusable analysis platform","created":"2024-03-06","cited_by_count":1}],"next_cursor":null}