arXiv (OAI Expanded)
open access
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluations that frontier-model governance depends on. The Elicitation Game found that fine-tuning elicits hidden capability from sandbagging model organisms wh
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
- Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities#794242
- Multi‐Model Ensembles in Ecosystem Modeling: Challenges and Best Practices for Decision‐Making#495638
- FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs#822563
- Insights into the development and key factors of five European governance innovations for forest ecosystem service provision#1106588
- Distilling Foundation Models for Agentic What-If Reasoning:Cost, Latency, and Governance in a Hybrid LLM+SLM Architecture#1110478
Record · ID 790223
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