Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility

ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than input-local interactions. We test this in retrieval-augmented generation (RAG), where evidence utility can be measured under controlled interventions.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• rag
• efficiency