{"total":29,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50,"area":null},{"id":"2306.10512","title":"Position: AI Evaluation Should Learn from How We Test Humans","created":"2023-06-18","cited_by_count":36,"area":null},{"id":"2305.14610","title":"This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models","created":"2023-05-24","cited_by_count":32,"area":null},{"id":"2309.01686","title":"MathAttack: Attacking Large Language Models Towards Math Solving Ability","created":"2023-09-04","cited_by_count":32,"area":null},{"id":"2402.15833","title":"Prompt Perturbation Consistency Learning for Robust Language Models","created":"2024-02-24","cited_by_count":26,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2306.08891","title":"Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation","created":"2023-06-15","cited_by_count":24,"area":null},{"id":"2411.03538","title":"Long Context RAG Performance of Large Language Models","created":"2024-11-05","cited_by_count":23,"area":null},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2406.10504","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","created":"2024-06-15","cited_by_count":19,"area":null},{"id":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2503.10690","title":"Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2503.01508","title":"Enabling AI Scientists to Recognize Innovation: A Domain-Agnostic Algorithm for Assessing Novelty","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2305.12737","title":"The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2306.05079","title":"Enhancing Robustness of AI Offensive Code Generators via Data Augmentation","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2402.04609","title":"Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2406.10802","title":"KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2403.08425","title":"Specification Overfitting in Artificial Intelligence","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2305.03517","title":"Few-shot Domain-Adaptive Visually-fused Event Detection from Text","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2309.12294","title":"Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2502.19669","title":"Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null}],"next_cursor":null}