{"list":"other","total":54,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"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":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"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":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"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":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2411.00836","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","created":"2024-10-29","cited_by_count":146},{"id":"2409.13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","created":"2024-09-10","cited_by_count":137},{"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":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99},{"id":"2402.04379","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","created":"2024-02-06","cited_by_count":93},{"id":"2303.05352","title":"Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering","created":"2023-03-07","cited_by_count":86},{"id":"2306.06283","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","created":"2023-06-09","cited_by_count":86},{"id":"2411.00855","title":"Vision-Language Models Can Self-Improve Reasoning via Reflection","created":"2024-10-30","cited_by_count":69},{"id":"2401.06949","title":"ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization","created":"2024-01-13","cited_by_count":61},{"id":"2403.13315","title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","created":"2024-03-20","cited_by_count":57},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56},{"id":"2304.02711","title":"Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning","created":"2023-04-05","cited_by_count":50},{"id":"2402.05015","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","created":"2024-02-07","cited_by_count":48},{"id":"2405.08807","title":"SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation","created":"2024-05-14","cited_by_count":48},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47},{"id":"2306.13952","title":"Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools","created":"2023-06-24","cited_by_count":45},{"id":"2401.14423","title":"Prompt Design and Engineering: Introduction and Advanced Methods","created":"2024-01-24","cited_by_count":45},{"id":"2402.05200","title":"Are LLMs Ready for Real-World Materials Discovery?","created":"2024-02-07","cited_by_count":40},{"id":"2410.23326","title":"MassSpecGym: A benchmark for the discovery and identification of molecules","created":"2024-10-30","cited_by_count":38},{"id":"2402.05138","title":"SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark","created":"2024-02-06","cited_by_count":35},{"id":"2305.11186","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","created":"2023-05-17","cited_by_count":28},{"id":"2411.04118","title":"Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?","created":"2024-11-06","cited_by_count":28},{"id":"2306.06548","title":"Inductive reasoning in humans and large language models","created":"2023-06-11","cited_by_count":24},{"id":"2410.14702","title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","created":"2024-10-06","cited_by_count":22},{"id":"2410.22456","title":"Image2Struct: Benchmarking Structure Extraction for Vision-Language Models","created":"2024-10-29","cited_by_count":19},{"id":"2207.01079","title":"DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles","created":"2022-07-03","cited_by_count":17},{"id":"2403.05075","title":"Benchmarking Large Language Models for Molecule Prediction Tasks","created":"2024-03-08","cited_by_count":17},{"id":"2407.16867","title":"From Text to Insight: Large Language Models for Materials Science Data Extraction","created":"2024-07-23","cited_by_count":15},{"id":"2405.10986","title":"Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models","created":"2024-05-15","cited_by_count":9},{"id":"2410.20494","title":"MatViX: Multimodal Information Extraction from Visually Rich Articles","created":"2024-10-27","cited_by_count":8},{"id":"2403.12196","title":"Leveraging Large Language Models to Detect npm Malicious Packages","created":"2024-03-18","cited_by_count":6},{"id":"2304.10510","title":"Censoring chemical data to mitigate dual use risk","created":"2023-04-20","cited_by_count":3},{"id":"2310.08101","title":"Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques","created":"2023-10-12","cited_by_count":3}],"next_cursor":null}