cs.AINov 19, 2026

Anchor and Check: Deterministic Cross-Prompt, Cross-Model Reconciliation for Auditable LLM Decisions

Authors: Sivakameswara Reddy Chejarla

Abstract

Pipelines that let a large language model (LLM) make discrete decisions need to know which decisions they may act on unattended, and a record that explains each one. We study a small, fully specified reconciliation contract: commit the target model's greedy answer (the anchor), draw one or two greedy checks that reach the answer by a different route (an alternate prompt, or a model from another family), and let a pure function return one of five outcomes, of which only Agree is acted on. On 48,000 model-item evaluations over 6,000 questions, with every method given access to verbalized confidence as a tie-breaker, the main finding concerns where calls come from: pooling another family's samples raises semantic entropy's AUROC by 1.7 to 4.0 points at every budget, and a same-model temperature check is the weakest design. As complete pipelines, the point estimates of the three-call contract and pooled semantic entropy over 3 or 5 samples differ by less than one point, with intervals containing zero. As detectors of the anchor's errors, the contract is ahead of pooled entropy with 3 and 5 samples under both tie-breaker conventions; with 10 samples the point estimates differ by less than one point and the sign depends on the convention. Under the strict Agree gate it automates 70% of items and still acts on 16% of errors. What the contract adds is a fixed committed answer, an explicit outcome and a decision replayable from its record; generation itself was not reproducible on the hosted API.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility

    Aug 10, 2026Siyang Wu, Yibo Jiang, Bryon AragamPrompt SensitivityLLM Evaluation

  2. Hidden Commitment: When Language Models Silently Pick a Side and How Steering Can Surface It

    Oct 28, 2026Samuel Dawit Assefa, Jae Won ChoKnowledge Conflicts in Language ModelsLanguage Model Auditing