AuDQ: Auditable Data Quality through Agentic Rule Discovery

The validation of data, such as customer and employee data, is an important task in many organizations. Errors in data can have severe consequences. For example, a wrong drug unit in a patient record can lead to life-threatening medication errors, and a missing street number in an address to failed deliveries. Companies often employ rule-based enterprise data quality (DQ) tools, which allow domain experts to specify rules to validate the data over time. While rule-based DQ tools are computationally efficient and provide explainable reports, maintaining a comprehensive rule set manually is challenging, as domain experts often overlook essential rules, especially in complex domains and large data volumes. Hence, closing these gaps remains an open problem in practice. In this paper, we address the challenge of automated DQ rule generation. For this, we formalize a generalizable generate-filter framework and introduce LeDQeR, an LLM-based DQ rule generation approach. First, a large language model (LLM) generates candidates rules from an observed dirty data tuple for a given rule-based DQ tool syntax. Second, we apply four filter techniques that ensure the (i) executability, (ii) correctness, and (iii) generalizability, and avoid (iv) redundancy of the generated rules. An extensive experimental evaluation suggests that LeDQeR is able to produce effective and compact rule sets for various datasets and error types.

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.

Data quality assessment is a critical prerequisite for effective data analytics and data-driven decision-making, yet it remains a challenging task due to the inherently context-dependent nature of data quality. Existing approaches often rely on static rules or manual assessment strategies, limiting their adaptability to diverse usage scenarios and constraining automation at scale. Recent advances in artificial intelligence, particularly large language models, offer new opportunities for automating data quality assessment, but raise concerns related to reliability, grounding, and execution safety. In this paper, we propose a unified agentic-retrieval framework for autonomous context-aware data quality assessment. The framework interprets natural-language descriptions of intended data usage, derives context-aware assessment strategies, and generates executable validation logic through a multi-agent workflow. To ensure operational reliability, the framework introduces a feasibility validation stage that evaluates the realism and executability of generated assessment specifications before execution, enabling iterative refinement when necessary. Accepted validation logic is executed deterministically to guarantee reproducible and auditable results. We implement the proposed framework as an end-to-end prototype and evaluate it across multiple usage scenarios applied to the same dataset. The results demonstrate that assessment outcomes adapt meaningfully to different intended uses, while feasibility-gated execution reduces unrealistic or non-executable rule generation. The proposed approach provides a practical foundation for deploying autonomous yet controlled data quality assessment in modern data-driven environments.