arXiv (All)
open access
Extracting Forgotten Prompts from Targeted Unlearned Models
Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal responses might leave traces of unlearning, and recent attacks have been able to successfully recover some of the unlearned knowledge. In this paper, we
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning#1051475
- CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering#1131771
- CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering#1122221
- Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families#1084683
- Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs#1064694
Record · ID 926559
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive