{"total":21,"rows":[{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2603.04426","title":"Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2602.00767","title":"BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2606.30252","title":"Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2602.00533","title":"Convergent World Representations and Divergent Tasks","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.20225","title":"Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.02755","title":"Out-of-Distribution Generalization of Risk Aversion in Language Models","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.23394","title":"Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2609.37914","title":"The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.04510","title":"Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.20449","title":"The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2608.05611","title":"FOCUS: Decoupling Expert Personas in LLMs to Enhance Domain Expert Capabilities","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2610.03251","title":"Learning a Fact Is Not Learning How to Retrieve It","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14937","title":"Predicting how model propensities generalize out of distribution","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}