{"total":27,"rows":[{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2303.06273","title":"Consistency Analysis of ChatGPT","created":"2023-03-11","cited_by_count":37,"area":null},{"id":"2311.01152","title":"Predicting Question-Answering Performance of Large Language Models through Semantic Consistency","created":"2023-11-02","cited_by_count":28,"area":null},{"id":"2308.09138","title":"Semantic Consistency for Assuring Reliability of Large Language Models","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2501.11041","title":"Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach","created":"2025-01-19","cited_by_count":14,"area":null},{"id":"2505.00268","title":"Consistency in Language Models: Current Landscape, Challenges, and Future Directions","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2502.15924","title":"Improving Consistency in Large Language Models through Chain of Guidance","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2408.01963","title":"A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios","created":"2024-08-04","cited_by_count":8,"area":null},{"id":"2407.04173","title":"Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2605.11928","title":"When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2305.10519","title":"Statistical Knowledge Assessment for Large Language Models","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2512.23712","title":"STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability","created":"2025-11-27","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":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2503.18562","title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2605.10516","title":"Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2407.17150","title":"SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2410.15440","title":"Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2502.01220","title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2511.12728","title":"On the Brittleness of LLMs: A Journey around Set Membership","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2512.14717","title":"Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.23932","title":"A Proof-of-Concept for Explainable Disease Diagnosis Using Large Language Models and Answer Set Programming","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2605.04665","title":"Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2608.10806","title":"Assessing Reliability of BERT-Based Models on Question Answering Tasks","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}