arXiv AI

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering

The paper proposes a causal prompt engineering framework that encodes a domain expert’s decision logic—termed an Expert Mental Model (EMM)—into large language models (LLMs) to mitigate hallucinations arising from missing knowledge. By formalizing factor formulation, factor monotonization, and monotonicity-preserving hierarchical structuring, the framework reduces the elicitation burden from millions of combinations to a manageable set, enabling a four-step EMM construction algorithm. The approach allows formal measurement of hallucination rates in tacit expert knowledge and is validated in grant proposal evaluation, cybersecurity design, and clinical diagnosis.

arXiv Computation and Language

Oct 23

Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study

The paper presents an empirical taxonomy of eleven hallucination sub‑types in large language models (LLMs) that generate UML class diagrams from natural language requirements, organized into Prompt Faithfulness, Code Faithfulness, and Reasoning Quality. The taxonomy was derived from 60 manually annotated DeepSeek‑R1 traces and applied to additional traces, revealing model‑dependent failure patterns and a negative association between requirement complexity and Prompt Faithfulness errors. A mitigation experiment with Qwen3‑based models showed that adding Prompt Faithfulness and Reasoning Quality constraints to the prompt improved the F1 score by 4.0 percentage points, while post‑hoc Code Faithfulness review offered no consistent benefit.

By Mojdeh Rahmanian, Foutse Khomh, Ashkan Sami, Yanchao Yu

llms safety

arXiv AI

1d ago

Combining Relevant Expert Knowledge Using Mixtures of Feedback Fuzzy Cognitive Maps

The paper proposes a method for combining expert knowledge using mixtures of feedback fuzzy cognitive maps (FCMs) guided by a relevance criterion adapted from legal evidence theory. An answer is deemed relevant only if it is both probative and material to the query, and this relevance is used to weight and mix expert FCMs into a query‑specific knowledge network. The authors introduce a Bayes‑like de‑mixing theorem to estimate posterior‑like FCMs and demonstrate the approach on synthetic FCMs derived from a 13‑node expert model of ischemic‑stroke risk.

By Olaoluwa Adigun, Akash Kumar Panda, Bart Kosko

agents

arXiv AI

Sep 21

Auditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5

The paper presents a framework and results of a multi-dimensional analysis of GPTKB v1.5, a 100‑million‑fact knowledge base elicited from GPT‑4.1. It shows that the LLM’s factual knowledge differs markedly from established knowledge bases and that its accuracy is lower than suggested by prior benchmarks. The study also identifies inconsistency, ambiguity, and hallucinations as major issues, pointing to future research directions in neuro‑symbolic AI for extracting, consolidating, and verifying factual LLM knowledge.

By Shrestha Ghosh, Luca Giordano, Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

llms rag benchmarks safety

arXiv AI

Sep 7

GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion

The paper introduces GRACE, a framework that breaks down large language model (LLM) responses into atomic claims and grounds them against trusted knowledge priors using a weighted bipartite graph. Edge weights enable weighted centrality analysis to classify claims as Grounded, Refuted, or Boundary, identifying hallucinations and frontier knowledge. An objective called Return on Attention (RoA) prioritizes expert review only for high‑uncertainty claims, and verified claims become new evidence anchors, creating a loop that expands the knowledge base across iterations.

By John Seon Keun Yi, Joshua R. Minot, Dokyun Lee

llms rag agents safety

arXiv AI

Sep 7

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

The paper explores using a language model’s low‑level symbolic skill—specifically SQL—to detect hallucinations without fine‑tuning. By having the model construct an SQL database from reference documents, it can reason over both the source and the model’s output, creating a neurosymbolic check. Experiments on RAGTruth and DiaHalu show this method outperforms direct prediction and rivals state‑of‑the‑art detectors, highlighting the value of leveraging inherent symbolic competences in LLMs.

By Renato Vukovic, Hsien-chin Lin, Carel van Niekerk, Benjamin Ruppik, Michael Heck, Shutong Feng, Nurul Lubis, Milica Gasic

llms fine-tuning benchmarks safety data-engineering

arXiv AI

Aug 26

Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge

arXiv:2601.10485v5 Announce Type: replace Abstract: Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compared to General Knowledge Graphs (GKGs). Existing t...

By Runhao Zhao, Weixin Zeng, Wentao Zhang, Chong Chen, Zhengpin Li, Xiang Zhao, Lei Chen

arXiv AI

Jul 31

Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring

arXiv:2607. 26220v1 Announce Type: cross Abstract: Context: Large Language Models (LLMs) offer natural-language flexibility for automated requirements elicitation but frequently generate structurally invalid requirements and logical inconsistencies, lacking formal correctness guarantees.

By Ahmed Ibrahim

llms agents

arXiv Machine Learning

Jul 27

Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA

arXiv:2607. 21680v1 Announce Type: new Abstract: Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the naked eye.

By Takato Yasuno

llms rag agents fine-tuning efficiency benchmarks

arXiv AI

Jun 9

Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations

arXiv:2507. 09751v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but exhibit problems with logical consistency in their output.

By Bradley P. Allen, Prateek Chhikara, Thomas Macaulay Ferguson, Filip Ilievski, Paul Groth

llms rag benchmarks safety

arXiv AI

Oct 27

Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators

arXiv:2605.07600v2 Announce Type: replace-cross Abstract: Recent methods for improving LLM mathematical reasoning, whether through MCTS-based test-time search or causal graph-guided knowledge injecti...

By Tsuyoshi Okita

llms benchmarks

arXiv AI

Jul 28

Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming

arXiv:2607. 23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically sound.

By Zirong Chen, Meiyi Ma

llms benchmarks

arXiv AI

Aug 18

Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot

arXiv:2608. 15382v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty.

By Ummara Mumtaz, Aimen Noor, Awais Ahmed

llms

Related stories