{"total":34,"rows":[{"id":"2504.04715","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35,"area":null},{"id":"2502.12150","title":"Idiosyncrasies in Large Language Models","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2506.06975","title":"Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2508.19843","title":"SoK: Large Language Model Copyright Auditing via Fingerprinting","created":"2025-08-27","cited_by_count":15,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2509.26598","title":"Are Robust LLM Fingerprints Adversarially Robust?","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2603.01919","title":"Real Money, Fake Models: Deceptive Model Claims in Shadow APIs","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2504.14871","title":"Natural Fingerprints of Large Language Models","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2511.00847","title":"Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers","created":"2025-11-02","cited_by_count":6,"area":null},{"id":"2511.02620","title":"Verifying LLM Inference to Detect Model Weight Exfiltration","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2604.06188","title":"LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2607.10252","title":"One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions","created":"2026-07-11","cited_by_count":6,"area":null},{"id":"2602.11083","title":"Token-Efficient Change Detection in LLM APIs","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2510.06738","title":"AWM: Accurate Weight-Matrix Fingerprint for Large Language Models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2602.22700","title":"IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2605.29524","title":"KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.16100","title":"Your \"Pro\" LLM Subscription May Actually Be \"Free\": Exposing Fingerprint Spoofing Risks in LLM Inference Services","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2511.20621","title":"DiFR: Inference Verification Despite Nondeterminism","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2607.19510","title":"Total Variation Distance Estimation in Autoregressive Models","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2502.06560","title":"Position: It's Time to Act on the Risk of Efficient Personalized Text Generation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2510.27498","title":"Minimax-Optimal Two-Sample Test with Sliced Wasserstein","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2603.22404","title":"Computational Arbitrage in AI Model Markets","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2603.25638","title":"Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2608.05086","title":"Item Response Theory for AI Safety","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2505.20433","title":"Kernel Quantile Embeddings and Associated Probability Metrics","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2509.25813","title":"RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2605.25673","title":"Referential Security as a New Paradigm for AI Evaluations","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.16177","title":"Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.16391","title":"Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.38831","title":"Forging LLM Authorship Fingerprints with Targeted Rewriting","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05533","title":"What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13855","title":"SLICE: Sequential Likelihood-Free Inference via Conformal E-Values","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}