mlsanityData to 7 Oct 2026

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology

arXiv 2502.17026 ↗First posted 24 Feb 2025cs.CL cs.AI cs.SCcited by 24

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Understanding the uncertainty in large language model (LLM) explanations is important for evaluating their faithfulness and reasoning consistency, and thus provides insights into the reliability of LLM's output regarding a question. In this work, we propose a novel framework that quantifies uncertainty in LLM explanations through a reasoning topology perspective. By designing a structural elicitation strategy, we guide the LLMs to frame the explanations of an answer into a graph topology. This process decomposes the explanations into the knowledge related sub-questions and topology-based reasoning structures, which allows us to quantify uncertainty not only at the semantic level but also from the reasoning path. It further brings convenience to assess knowledge redundancy and provide interpretable insights into the reasoning process. Our method offers a systematic way to interpret the LLM reasoning, analyze limitations, and provide guidance for enhancing robustness and faithfulness. This work pioneers the use of graph-structured uncertainty measurement in LLM explanations and demonstrates the potential of topology-based quantification.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 39 of its 54 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

39 of 54 references.

References · 39

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  7. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  8. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  9. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  10. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  11. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  12. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
27 more
  1. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  2. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  3. 2023A Comprehensive Overview of Large Language Modelscited by 639
  4. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  5. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  6. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  7. 2020Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease predictioncited by 368
  8. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  9. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  10. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  11. 2024A Careful Examination of Large Language Model Performance on Grade School Arithmeticcited by 188
  12. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 147
  13. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  14. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  15. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  16. 2024To Believe or Not to Believe Your LLMcited by 120
  17. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  18. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  19. 2024Can Language Models Solve Olympiad Programming?cited by 70
  20. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 68
  21. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  22. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 53
  23. 2018Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matchingcited by 45
  24. 2023Quantifying Uncertainty in Natural Language Explanations of Large Language Modelscited by 31
  25. 2024LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentationcited by 22
  26. 2023Large Language Models are legal but they are not: Making the case for a powerful LegalLLMcited by 12
  27. 2024Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Spacecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 17.

24 papers.

Sort:

By area:

  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  2. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  3. 2025An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainabilitycited by 15
  4. 2025Generative AI in Transportation Planning: A Surveycited by 8
  5. 2026Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weightingcited by 8
  6. 2026Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decompositioncited by 5
  7. 2025Large Language Newsvendor: Decision Biases and Cognitive Mechanismscited by 4
  8. 2026Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Modelscited by 4
  9. 2026Unveiling the Entropy Dynamics of Chain-of-Thought Reasoningcited by 4
  10. 2025All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoningcited by 3
  11. 2026SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratiocited by 3
  12. 2026Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attributioncited by 2
12 more
  1. 2026A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Modelscited by 2
  2. 2026From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Modelscited by 1
  3. 2026"I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Timecited by 1
  4. 2026Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervisioncited by 1
  5. 2025Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask NLP evaluationcited by 0
  6. 2026Fact-Checking with Large Language Models via Probabilistic Certainty and Consistencycited by 0
  7. 2026A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Modelscited by 0
  8. 2026CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systemscited by 0
  9. 2026TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimizationcited by 0
  10. 2026Position: Uncertainty Quantification in LLMs is Just Unsupervised Clusteringcited by 0
  11. 2026Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Frameworkcited by 0
  12. 2026GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Grounding LLM Reasoning with Knowledge Graphs
  2. 2024Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
  3. 2026Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning
  4. 2024Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective
  5. 2024Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data
  6. 2025Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
  7. 2023XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
  8. 2025KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs