Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule

arXiv:2610.36169v1 Announce Type: new Abstract: A retrieval-augmented language model answers from two sources, the retrieved context and its own knowledge, and the two disagree whenever the context is incomplete or wrong. Existing methods settle the disagreement with a rule fixed at design time: follow the context, amplify it in proportion to how far it moves the model, or trust the model's memory. Each rule is confidently wrong in some deployment. In a decision-theoretic model of two sources, the score of any fixed rule is linear in the share of reliable contexts while the best attainable score is convex, so every fixed rule is beaten wherever it is not exactly optimal; and a symmetric divergence between the two sources, the signal adaptive decoding uses, carries no information about which one is right. Resolving a conflict therefore needs two inputs that no existing method keeps: evidence about each source separately, and a prior on how often the context is right. We test these claims on GRACE, a benchmark that intervenes on the knowledge-graph context of a fixed question, so that what the model knows, what the context says and what is true are measured separately. There, every baseline from four families is strong on right contexts or on wrong ones, never on both. We then build the two inputs: the model states its knowledge as notes, a small policy voices each note with a calibrated confidence, a reader answers in two voices, and a selector commits or abstains under a prior $\pi$ applied as an exact prior shift. With $\pi$ set to the true share of right contexts, the sys

No claim about AI's effect on society.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   2b707e81-81cd-48ed-96dc-53faab0a24a0
           https://arxiv.org/abs/2610.36169
   ↓
EVIDENCE   1 extracted excerpt
   ↓
MODEL RUN  1 run, methodology 1.0.1
   ↓
SCORE      0  (Mixed or uncertain)
   ↓
CONFIDENCE 80%