arXiv (All)
open access
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment
The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains. In this work, we propose the Piggyback Hypothesis: the
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
- Re-thinking the Arbitrary Mapping of Signier and Signied: A Symmetry and Symmetry-Breaking Perspective#85050
- Neural Language Models’ sensitivity to long-distance dependencies and their island constraints is not universal: a comparison between English and Dutch humans and models#331597
- Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts#139019
- Can One-Shot Test-Time Data Augmentation Help with Generalization?#973052
- When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift#821862
Record · ID 1156380
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