Domain-Specific Hallucination Detection in Large Language Models

• URL: http://arxiv.org/abs/2609.11878v1
• Date: Thu, 10 Sep 2026 17:45:36 GMT
• Title: Domain-Specific Hallucination Detection in Large Language Models
• Abstract summary: Large language models generate fluent text that can contain unfaithful claims.<n>We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection. Evaluated on the HaluEval benchmark, our pipeline achieves F1=0.915 and AUROC=0.977 on general-domain tasks, with per-task F1 scores of 0.97 (QA), 0.96 (Summarization), and 0.82 (Dialogue). MC Dropout inference further improves accuracy to 93.2%. A context ablation study confirms the model performs genuine entailment reasoning rather than exploiting surface patterns, with summarization F1 dropping 24% when knowledge context is removed. Learning curve analysis reveals that 25% of training data captures 77% of full-data performance. Beyond detection, we apply Direct Preference Optimization (DPO) to a Qwen2.5-0.5B generator, reducing its hallucination rate from 85.5% to 37.7% (55.9% relative reduction) as measured by our detector. Cross-domain evaluation on the SciFact biomedical benchmark shows that general-domain training transfers poorly (F1=0.52), motivating domain-specific fine-tuning. PubMedBERT fine-tuned on SciFact achieves F1=0.63 and AUROC=0.81, demonstrating that domain-matched pre-training is the strongest adaptation strategy. Code and models are available at https://github.com/varunteja99/hallucination-detection-nlp

Related papers

• Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2 [0.0]
  Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model.<n>This paper presents a benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset.
  arXiv  Detail & Related papers  (2026-09-10T00:53:20Z)
• AnomalyGen: Enhancing Log-Based Anomaly Detection with Code-Guided Data Augmentation [42.87177529900358]
  AnomalyGen is a novel framework that augments training data by synthesizing labeled log sequences from source code.<n> Evaluations on HDFS and Zookeeper across 12 diverse anomaly detection models show AnomalyGen consistently improves performance.
  arXiv  Detail & Related papers  (2026-04-13T07:24:43Z)
• Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation [44.50339042016925]
  We propose a planner-executor model that generates bond graphs with 3D coordinates using a latent multi-scale plan for global context.<n>HLTF achieves 98.8% atom stability and 92.9% valid-and-unique, improving PoseBusters validity to 94.0% (+0.9 over the strongest reported baseline)<n>On GEOM-DRUGS, HLTF attains 85.5%/85.0% validity/valid-unique-novel without post-processing and 92.2%/91.2% after standardized relaxation.
  arXiv  Detail & Related papers  (2026-03-28T03:48:13Z)
• Predictive Coding and Information Bottleneck for Hallucination Detection in Large Language Models [0.8552050317027305]
  Hallucinations in Large Language Models (LLMs) remain a critical barrier to high-stakes deployment.<n>We introduce [Model Name], a hybrid detection framework that combines neuroscience-inspired signal design with supervised machine learning.
  arXiv  Detail & Related papers  (2026-01-22T05:00:21Z)
• Generalization Gaps in Political Fake News Detection: An Empirical Study on the LIAR Dataset [0.764671395172401]
  We present a diagnostic evaluation of nine machine learning algorithms on the LIAR benchmark.<n>We uncover a hard "Performance Ceiling", with fine-grained classification not exceeding a weighted F1-score of 0.32 across models.<n>A massive "Generalization Gap" in tree-based ensembles, which achieve more than 99% training accuracy but collapse to approximately 25% on test data.
  arXiv  Detail & Related papers  (2025-12-20T23:08:18Z)
• Detecting AI Hallucinations in Finance: An Information-Theoretic Method Cuts Hallucination Rate by 92% [4.693270291878929]
  Large language models (LLMs) produce fluent but unsupported answers - hallucinations.<n>We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model's semantic entropy and the capacity of available evidence.
  arXiv  Detail & Related papers  (2025-12-02T05:25:48Z)
• CRTRE: Causal Rule Generation with Target Trial Emulation Framework [47.2836994469923]
  We introduce a novel method called causal rule generation with target trial emulation framework (CRTRE) CRTRE applies randomize trial design principles to estimate the causal effect of association rules. We then incorporate such association rules for the downstream applications such as prediction of disease onsets.
  arXiv  Detail & Related papers  (2024-11-10T02:40:06Z)
• Enhancing Diagnostic Reliability of Foundation Model with Uncertainty Estimation in OCT Images [41.002573031087856]
  We developed a foundation model with uncertainty estimation (FMUE) to detect 11 retinal conditions on optical coherence tomography ( OCT) FMUE achieved a higher F1 score of 96.76% than two state-of-the-art algorithms, RETFound and UIOS, and got further improvement with thresholding strategy to 98.44%. Our model is superior to two ophthalmologists with a higher F1 score (95.17% vs. 61.93% &71.72%)
  arXiv  Detail & Related papers  (2024-06-18T03:04:52Z)
• RULSurv: A probabilistic survival-based method for early censoring-aware prediction of remaining useful life in ball bearings [39.58317527488534]
  We introduce a novel and flexible method for early fault detection using Kullback-Leibler divergence and RUL estimation.<n>We demonstrate our approach in the XJTU-SY dataset using a 5-fold cross-validation strategy across three different operating conditions.<n>Our approach achieves a mean cumulative relative accuracy (CRA) of 0.7586 over 5 bearings under the highest load, which improves over several state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-05-02T16:17:29Z)
• Predicting Overtakes in Trucks Using CAN Data [51.28632782308621]
  We investigate the detection of truck overtakes from CAN data. Our analysis covers up to 10 seconds before the overtaking event. We observe that the prediction scores of the overtake class tend to increase as we approach the overtake trigger.
  arXiv  Detail & Related papers  (2024-04-08T17:58:22Z)
• A Federated Learning Framework for Stenosis Detection [70.27581181445329]
  This study explores the use of Federated Learning (FL) for stenosis detection in coronary angiography images (CA) Two heterogeneous datasets from two institutions were considered: dataset 1 includes 1219 images from 200 patients, which we acquired at the Ospedale Riuniti of Ancona (Italy) dataset 2 includes 7492 sequential images from 90 patients from a previous study available in the literature.
  arXiv  Detail & Related papers  (2023-10-30T11:13:40Z)
• Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition [6.917786124918387]
  We compare Transformer models that are trained from scratch to fine-tuned BERT-based LLMs. We examine the impact of an additional CRF layer on such models to encourage contextual learning.
  arXiv  Detail & Related papers  (2022-10-23T16:27:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.