# Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction

arXiv: https://arxiv.org/abs/2605.27706 · HTML: https://mlsanity.com/paper/2605.27706/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs](https://mlsanity.com/paper/2410.08020/) (2024)
- [Knowledge Graph-Enhanced Large Language Models via Path Selection](https://mlsanity.com/paper/2406.13862/) (2024)
- [HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification](https://mlsanity.com/paper/2504.07069/) (2025)
- [Approximation algorithms for stochastic clustering](https://mlsanity.com/paper/1809.02271/) (2018)
- [String Submodular Functions with Curvature Constraints](https://mlsanity.com/paper/1303.3018/) (2013)
- [URSA: The Universal Research and Scientific Agent](https://mlsanity.com/paper/2506.22653/) (2025)
- [ResQue Greedy: Rewiring Sequential Greedy for Improved Submodular Maximization](https://mlsanity.com/paper/2505.13670/) (2025)
- [Providing Meaningful Data Summarizations Using Exemplar-based Clustering in Industry 4.0](https://mlsanity.com/paper/2105.12026/) (2021)
- [Explainable Clustering via Exemplars: Complexity and Efficient Approximation Algorithms](https://mlsanity.com/paper/2209.09670/) (2022)

## Built on by (most cited first, 1 of 1)

- [DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents](https://mlsanity.com/paper/2608.18524/) (2026)

## Abstract (arXiv)

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.