arXiv (All)
open access
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However, existing inference-time alignment methods typically optimize a single scalar score, so explicit safety constraints must either be ignored or
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
- Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds#924198
- Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds#919967
- Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling#1141471
- Decoding-time Realignment of Language Models#1199620
- HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix#1156105
Record · ID 1198964
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