{"total":16,"rows":[{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2507.07248","title":"MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2507.21782","title":"The Problem with Safety Classification is not just the Models","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2601.01584","title":"Steerability of Instrumental-Convergence Tendencies in LLMs","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2603.00061","title":"The Hidden Costs of Domain Fine-Tuning: Pii-Bearing Data Degrades Safety and Increases Leakage","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.14723","title":"Beyond Creed: A Non-Identity Safety Condition A Strong Empirical Alternative to Identity Framing in Low-Data LoRA Fine-Tuning","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2607.14888","title":"Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2511.06073","title":"Stemming Hallucination in Language Models Using a Licensing Oracle","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.03648","title":"Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.28843","title":"The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.05158","title":"Safe Evolution with Circuit Anchors","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2609.11291","title":"Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.27333","title":"Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}