{"total":19,"rows":[{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290,"area":null},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44,"area":null},{"id":"2402.10693","title":"Exploring Precision and Recall to assess the quality and diversity of LLMs","created":"2024-02-16","cited_by_count":29,"area":null},{"id":"2408.11832","title":"OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs","created":"2024-08-06","cited_by_count":28,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","cited_by_count":13,"area":null},{"id":"2307.00101","title":"Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2405.05583","title":"OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2207.08982","title":"Selection Bias Induced Spurious Correlations in Large Language Models","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2110.08094","title":"Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2410.12878","title":"Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2503.10881","title":"SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2606.11203","title":"LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2401.14869","title":"F-Eval: Assessing Fundamental Abilities with Refined Evaluation Methods","created":"2024-01-26","cited_by_count":0,"area":null}],"next_cursor":null}