Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement

原文：Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement

作者：Kardelen Subasi, Jarosław A. Chudziak

来源：arXiv cs.AI（人工智能）

正文

Computer Science > Databases

arXiv:2610.29669v1 (cs)

[Submitted on 21 Oct 2026]

Title:Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement

Authors:Kardelen Subasi, Jarosław A. Chudziak

View a PDF of the paper titled Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement, by Kardelen Subasi and 1 other authors

View PDF

HTML (experimental)

Abstract:LLM-generated records increasingly populate production information systems where they are treated as data assets subject to the same quality expectations as records from operational databases. A single such record can simultaneously satisfy and violate a quality rule: a grounded fact adjacent to a hallucination, a useful answer adjacent to a stereotype. Classical data cleaning cannot resolve this because the two judgments are incompatible over the same span; a single LLM judge cannot either, since it shares the training biases that produced the conflict. Existing interventions such as prompt engineering, chain-of-thought, and RLHF reduce surface error rates but provide no audit trail and cannot distinguish genuine remediation from blanket suppression. The question is whether a deterministic check over structured inter-agent records can catch the defects that referential checks alone miss. We present BiasGuard-D: two adversarial roles drawn from distinct model families exchange typed claim documents, a three-model quorum adjudicates by majority vote, and a combined referential-plus-semantic invariant validates the verdict. The semantic component fires on verdicts referential checks miss; removing the iterative loop drops invariant satisfaction sharply. The deliberation layer transfers from stereotype to hallucination remediation on HaluEval QA with only role-framing changes, raising right-answer recovery by 49 percentage points; the triage gate required a cross-family second auditor to maintain recall on objective hallucination. Every claim, vote, and instruction is stored as a typed record giving operators a provenance trail auditable under emerging AI regulations.

Comments:

Accepted at the International Conference on Cooperative Information Systems (CoopIS 2026)

Subjects:

Databases (cs.DB); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA)

Cite as:

arXiv:2610.29669 [cs.DB]

(or

arXiv:2610.29669v1 [cs.DB] for this version)

https://doi.org/10.48550/arXiv.2610.29669

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

数据库 · 人工智能 · 自然语言处理 · 多智能体

由「前沿雷达」于 2026-10-21 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。