arXiv (All)
open access
Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering
Sparse autoencoder (SAE)-based steering has been widely used to address knowledge conflicts by guiding LLMs to be more faithful to the contextual knowledge. Existing methods usually perform mass steering, which modifies a large batch of SAE features identified via correlation-based methods. However,
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
- Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence#353052
- Forecasting With LLMs: Improved Generalization Through Feature Steering#310820
- CoFEE: Reasoning Control for LLM-Based Feature Discovery#126533
- Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning#429342
- DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes#236516
Record · ID 985551
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