# Fast and Accurate Contextual Knowledge Extraction Using Cascading Language Model Chains and Candidate Answers

arXiv: https://arxiv.org/abs/2507.22921 · HTML: https://mlsanity.com/paper/2507.22921/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligence](https://mlsanity.com/paper/2201.04200/) (2022)
- [Validating Large Language Models with ReLM](https://mlsanity.com/paper/2211.15458/) (2022)
- [Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models](https://mlsanity.com/paper/2503.01781/) (2025)
- [Enterprise Large Language Model Evaluation Benchmark](https://mlsanity.com/paper/2506.20274/) (2025)
- [Multi-stage Deep Classifier Cascades for Open World Recognition](https://mlsanity.com/paper/1908.09931/) (2019)
- [Extracting Explainable Dates From Medical Images By Reverse-Engineering UNIX Timestamps](https://mlsanity.com/paper/2505.11451/) (2025)
- [Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work](https://mlsanity.com/paper/2507.02760/) (2025)

## Abstract (arXiv)

Language models can capture complex relationships in given text, but these are notorious for being costly and for producing information that does not exist (i.e., hallucinations). Furthermore, the resources invested into producing this information would be wasted if it were incorrect. We address these issues by proposing, implementing, and applying the Language Model Chain (LMC) algorithm. In this, a language model's response to a given prompt about given text is only correct if it exists in the collection of possible (i.e., candidate) answers, and text corresponding to incorrect responses is fed into a more predictive (but slower) language model. This process is repeated for a collection of language models, or until all predictions about the text are correct. We used the LMC algorithm to extract patient dates of birth from medical documents, and combining a collection of language models in a multi-stage cascade significantly increased prediction speed and accuracy over individual language models, while greatly reducing the number of corresponding hallucinations. We believe that the novel LMC algorithm significantly contributes to the knowledge extraction field, and that this should be explored much further in the future.