arXiv (All)
open access
Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train models toward fewer such claims. We show that these rewards are hacked by copying. A sentence copied from the passages i
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
- RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation#1248110
- Optimizing watermarks for large language models#1063703
- Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall#1117895
- Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation#972942
- Quantifying Retriever-Generator Alignment in RAG with Local Explanations#1247330
Record · ID 1343951
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