{"total":127,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368,"area":null},{"id":"2402.09391","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","created":"2024-02-14","cited_by_count":128,"area":null},{"id":"2402.06852","title":"ChemLLM: A Chemical Large Language Model","created":"2024-02-10","cited_by_count":106,"area":null},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2406.07599","title":"CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence","created":"2024-06-11","cited_by_count":62,"area":null},{"id":"2406.16976","title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","created":"2024-06-23","cited_by_count":61,"area":null},{"id":"2401.14818","title":"Developing ChemDFM as a large language foundation model for chemistry","created":"2024-01-26","cited_by_count":52,"area":null},{"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,"area":null},{"id":"2505.08783","title":"CodePDE: An Inference Framework for LLM-driven PDE Solver Generation","created":"2025-05-13","cited_by_count":39,"area":null},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2406.07815","title":"Are Large Language Models Good Statisticians?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2410.23426","title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2406.06316","title":"Tx-LLM: A Large Language Model for Therapeutics","created":"2024-06-10","cited_by_count":25,"area":null},{"id":"2410.14182","title":"LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs","created":"2024-10-18","cited_by_count":25,"area":null},{"id":"2402.03781","title":"MolTC: Towards Molecular Relational Modeling In Language Models","created":"2024-02-06","cited_by_count":22,"area":null},{"id":"2406.09098","title":"SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models","created":"2024-06-13","cited_by_count":19,"area":null},{"id":"2409.13686","title":"The Impact of Large Language Models in Academia: from Writing to Speaking","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2409.13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","created":"2024-09-21","cited_by_count":18,"area":null},{"id":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17,"area":null},{"id":"2403.05075","title":"Benchmarking Large Language Models for Molecule Prediction Tasks","created":"2024-03-08","cited_by_count":17,"area":null},{"id":"2409.19667","title":"Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models","created":"2024-09-29","cited_by_count":17,"area":null},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"area":null},{"id":"2503.13503","title":"SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models","created":"2025-03-12","cited_by_count":15,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2402.01439","title":"From Words to Molecules: A Survey of Large Language Models in Chemistry","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2406.13193","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2509.20988","title":"AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search","created":"2025-09-25","cited_by_count":13,"area":null},{"id":"2504.09754","title":"Integrating Large Language Models for Automated Structural Analysis","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2410.19627","title":"Knowledge Graph Enhanced Language Agents for Recommendation","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2412.19994","title":"From Generalist to Specialist: A Survey of Large Language Models for Chemistry","created":"2024-12-28","cited_by_count":11,"area":null},{"id":"2510.16824","title":"ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning","created":"2025-10-19","cited_by_count":11,"area":null},{"id":"2402.00024","title":"Can Large Language Models Understand Molecules?","created":"2024-01-05","cited_by_count":10,"area":null},{"id":"2402.12391","title":"Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data","created":"2024-02-15","cited_by_count":10,"area":null},{"id":"2405.08989","title":"What is it for a Machine Learning Model to Have a Capability?","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2502.11149","title":"Large Language-Geometry Model: When LLM meets Equivariance","created":"2025-02-16","cited_by_count":10,"area":null},{"id":"2406.14721","title":"1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2408.10285","title":"BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2505.02639","title":"Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2505.03049","title":"34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2505.15054","title":"MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation","created":"2025-05-21","cited_by_count":9,"area":null},{"id":"2411.15221","title":"Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2502.20933","title":"MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models","created":"2025-02-28","cited_by_count":7,"area":null},{"id":"2510.19484","title":"KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge","created":"2025-10-22","cited_by_count":7,"area":null},{"id":"2405.14766","title":"Evaluating Large Language Models for Public Health Classification and Extraction Tasks","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2502.09897","title":"Artificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction to Generation and Beyond","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2406.06777","title":"MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2407.20267","title":"A Large Encoder-Decoder Family of Foundation Models For Chemical Language","created":"2024-07-24","cited_by_count":5,"area":null},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2503.03135","title":"Bridging Molecular Graphs and Large Language Models","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2509.18487","title":"Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2305.17819","title":"Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2403.13830","title":"Bridging Text and Molecule: A Survey on Multimodal Frameworks for Molecule","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2403.15274","title":"Bioinformatics and Biomedical Informatics with ChatGPT: Year One Review","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2410.04601","title":"ProtoMed-LLM: An Automatic Evaluation Framework for Large Language Models in Medical Protocol Formulation","created":"2024-10-06","cited_by_count":4,"area":null},{"id":"2503.04734","title":"What can large language models do for sustainable food?","created":"2025-02-02","cited_by_count":4,"area":null},{"id":"2505.16340","title":"Improving Chemical Understanding of LLMs via SMILES Parsing","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2509.23099","title":"How to Make Large Language Models Generate 100% Valid Molecules?","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.16590","title":"Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration","created":"2025-10-18","cited_by_count":4,"area":null},{"id":"2604.00002","title":"Benchmark for Assessing Olfactory Perception of Large Language Models","created":"2026-03-08","cited_by_count":4,"area":null},{"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,"area":null},{"id":"2502.17456","title":"Survey on Recent Progress of AI for Chemistry: Methods, Applications, and Opportunities","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2511.06530","title":"Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2512.01507","title":"SynthStrategy: Extracting and Formalizing Latent Strategic Insights from LLMs in Organic Chemistry","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2512.04629","title":"BioMedGPT-Mol: Multi-task Learning for Molecular Understanding and Generation","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2603.25857","title":"In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2605.01822","title":"Molecular Representations for Large Language Models","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2310.04674","title":"ReactionTeam: Teaming Experts for Divergent Thinking Beyond Typical Reaction Patterns","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2406.09612","title":"Automated Molecular Concept Generation and Labeling with Large Language Models","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2407.02028","title":"Why does in-context learning fail sometimes? Evaluating in-context learning on open and closed questions","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.13297","title":"SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2502.12669","title":"Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.00449","title":"Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2602.01771","title":"<SOG_k>: One LLM Token for Explicit Graph Structural Understanding","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2604.07669","title":"LLM-Guided Dynamic Action Spaces for Synthesizable Molecular Optimization","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2604.26498","title":"Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2608.21504","title":"ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation","created":"2026-08-21","cited_by_count":2,"area":null},{"id":"2312.03497","title":"Speculative Exploration on the Concept of Artificial Agents Conducting Autonomous Research","created":"2023-12-06","cited_by_count":1,"area":null},{"id":"2406.01808","title":"In-Context Learning of Physical Properties: Few-Shot Adaptation to Out-of-Distribution Molecular Graphs","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2407.08922","title":"Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2407.15141","title":"Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation","created":"2024-07-21","cited_by_count":1,"area":null},{"id":"2410.17005","title":"Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2504.08874","title":"Distilling and exploiting quantitative insights from Large Language Models for enhanced Bayesian optimization of chemical reactions","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2508.15392","title":"CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2509.12987","title":"Toward PDDL Planning Copilot","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.12135","title":"RTMol: Rethinking Molecule-text Alignment in a Round-trip View","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2602.03108","title":"ChemPro: A Progressive Chemistry Benchmark for Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.20065","title":"Multilingual Large Language Models do not comprehend all natural languages to equal degrees","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.12344","title":"Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Prediction","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.02934","title":"PolyReal: A Benchmark for Real-World Polymer Science Workflows","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.02351","title":"MolViBench: Evaluating LLMs on Molecular Vibe Coding","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2607.01800","title":"Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.02140","title":"Probing Chemical Language Models: Effects of Pre-training and Fine-tuning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.15630","title":"Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2312.07069","title":"Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2405.14203","title":"GLaD: Synergizing Molecular Graphs and Language Descriptors for Enhanced Power Conversion Efficiency Prediction in Organic Photovoltaic Devices","created":"2024-05-23","cited_by_count":0,"area":null}],"next_cursor":"100"}