arXiv (All)
open access
Contrastive Representation Shaping for LLM Unlearning
Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives defined in the prediction space. While effective at reducing forgotten content generation, such approaches may act as suppression: forgotten concepts ca
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
- LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents#925182
- LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents#920947
- Memory encoding reprograms neuronal transcriptional responses via durable chromatin remodeling#610853
- UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?#1132277
- Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure#1118157
Record · ID 1142612
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