English

Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction

Computation and Language 2026-05-28 v1 Information Retrieval

Abstract

We introduce CAROL (Chain-based Adaptive Reconfiguration Over Lattices), a probabilistic framework for test-time hallucination reduction in large language models. Rather than relying on token-level uncertainty, CAROL defines a semantic uncertainty measure based on the consistency between generated responses and a trusted context, inducing a string-submodular objective over a lattice of textual sequences. This formulation enables hallucination mitigation to be cast as a Markov chain accept-reject process with provable convergence and near-optimality guarantees, allowing the model to iteratively refine outputs toward semantic consistency. By operating at the level of meaning, CAROL unifies hallucination detection and mitigation within a single framework. Empirical results on question answering and multi-agent reasoning benchmarks show that CAROL significantly reduces hallucinations and improves reliability and interpretability compared to likelihood-based and retrieval-augmented baselines, while maintaining competitive computational efficiency.

Keywords

Cite

@article{arxiv.2605.27706,
  title  = {Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction},
  author = {Joan Vendrell Gallart and Solmaz Kia and Russell Bent and Michael Grosskopf},
  journal= {arXiv preprint arXiv:2605.27706},
  year   = {2026}
}
R2 v1 2026-07-22T07:35:44.948Z