# ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models

arXiv: https://arxiv.org/abs/2605.10328 · HTML: https://mlsanity.com/paper/2605.10328/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 69 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 30 of 45)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic](https://mlsanity.com/paper/2106.03794/) (2021)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [Amortizing intractable inference in large language models](https://mlsanity.com/paper/2310.04363/) (2023)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Bayesian Prompt Learning for Image-Language Model Generalization](https://mlsanity.com/paper/2210.02390/) (2022)
- [Training Chain-of-Thought via Latent-Variable Inference](https://mlsanity.com/paper/2312.02179/) (2023)
- [Retrieval-Augmented Generation with Hierarchical Knowledge](https://mlsanity.com/paper/2503.10150/) (2025)
- [COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences](https://mlsanity.com/paper/2106.00969/) (2021)
- [Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning](https://mlsanity.com/paper/2210.12217/) (2022)
- [Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models](https://mlsanity.com/paper/2503.17523/) (2025)
- [Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2505.20075/) (2025)
- [Large Language Models are overconfident and amplify human bias](https://mlsanity.com/paper/2505.02151/) (2025)
- [Bayesian model averaging: A systematic review and conceptual classification](https://mlsanity.com/paper/1509.08864/) (2015)

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

- [DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2605.15759/) (2026)

## Abstract (arXiv)

A central challenge in large-scale decision-making under incomplete information is estimating reliable probabilities. Recent approaches use Large Language Models (LLMs) to generate explanatory factors and coarse-grained probability estimates, which are then refined by a Na"ive Bayes model over factor combinations. However, sparse factor spaces often yield ``unknown'' predictions, while expanding factors increases noise and spurious correlations, weakening conditional independence and degrading reliability. To address these limitations, we propose textscAnchor, an aggregated Bayesian inference framework over a hierarchical factor space. It constructs dense factor hierarchies through iterative generation and clustering, maps contexts via hierarchical retrieval and refinement, and augments Na"ive Bayes with a Causal Bayesian Network to model latent factor dependencies. Experiments show that textscAnchor markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.