arXiv (All)
open access
Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints
Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently popular technique for such interventions is synthetic document fine-tuning (SDF), which aims to alter what the model believes. Ideal
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
- TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment#1118654
- Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models#1123051
- A Gravitational Interpretation of Safety Reversion under Fine-Tuning#1129317
- SALSA: Semi-Autonomous Literature Summarization Assistant#1036893
- SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics#1069780
Record · ID 1155702
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