Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

• URL: http://arxiv.org/abs/2410.15460v3
• Date: Tue, 07 Jan 2025 14:56:42 GMT
• Title: Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
• Authors: Shahrad Mohammadzadeh, Juan David Guerra, Marco Bonizzato, Reihaneh Rabbany, Golnoosh Farnadi,
• Abstract summary: This research investigates the relationship between the training process and the emergence of hallucinations.<n>We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training.<n>In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed.
• Score: 7.726825072908519
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.

Related papers

• HalluLens: LLM Hallucination Benchmark [49.170128733508335]
  Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination" This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks.
  arXiv  Detail & Related papers  (2025-04-24T13:40:27Z)
• Robust Hallucination Detection in LLMs via Adaptive Token Selection [25.21763722332831]
  Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment. We propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens. We achieve this robustness by an innovative formulation of the Hallucination detection task as Multiple Instance (HaMI) learning over token-level representations within a sequence.
  arXiv  Detail & Related papers  (2025-04-10T15:39:10Z)
• REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models [15.380441563675243]
  REFIND (Retrieval-augmented Factuality hallucINation Detection) is a novel framework that detects hallucinated spans within large language model (LLM) outputs. We propose the Context Sensitivity Ratio (CSR), a novel metric that quantifies the sensitivity of LLM outputs to retrieved evidence. REFIND demonstrated robustness across nine languages, including low-resource settings, and significantly outperformed baseline models.
  arXiv  Detail & Related papers  (2025-02-19T10:59:05Z)
• Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation [5.9079338934481225]
  We propose mitigating hallucination through knowledge distillation (KD) KD provides smoothed soft labels to a student model, reducing overconfidence and improving factual grounding. Experimental results on summarization benchmarks demonstrate that KD reduces hallucination compared to standard finetuning.
  arXiv  Detail & Related papers  (2025-02-16T23:05:36Z)
• HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses [0.12499537119440242]
  This paper proposes an explanation enhanced hallucination-detection model, coined as HuDEx. The proposed model provides a novel approach to integrate detection with explanations, and enable both users and the LLM itself to understand and reduce errors.
  arXiv  Detail & Related papers  (2025-02-12T04:17:02Z)
• The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States [0.5573267589690007]
  We focus on hallucinations involving information not used in training, which we determine by using recency to ensure the information emerged after a cut-off date. This study investigates these hallucinations by detecting them at sentence level using different internal states of various language models. Our results show that IAVs detect hallucinations as effectively as CEVs and reveal that answerable and unanswerable prompts are encoded differently as separate classifiers.
  arXiv  Detail & Related papers  (2024-12-22T15:08:24Z)
• Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning [16.883679810267342]
  Iterative Model-level Contrastive Learning (Iter-AHMCL) to address hallucination. This paper introduces a novel approach called Iterative Model-level Contrastive Learning (Iter-AHMCL) to address hallucination.
  arXiv  Detail & Related papers  (2024-10-16T00:15:40Z)
• ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability [27.325766792146936]
  hallucinations caused by insufficient parametric (internal) knowledge. Detecting such hallucinations requires disentangling how Large Language Models (LLMs) utilize external and parametric knowledge. We propose ReDeEP, a novel method that detects hallucinations by decoupling LLM's utilization of external context and parametric knowledge.
  arXiv  Detail & Related papers  (2024-10-15T09:02:09Z)
• Discovering Long-Term Effects on Parameter Efficient Fine-tuning [36.83255498301937]
  Pre-trained Artificial Neural Networks (Annns) exhibit robust pattern recognition capabilities. Annns and BNNs share extensive similarities with the human brain, specifically Biological Neural Networks (BNNs) Annns can acquire new knowledge through fine-tuning.
  arXiv  Detail & Related papers  (2024-08-24T03:27:29Z)
• Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability [83.0884072598828]
  Hallucinations come in many forms, and there is no universally accepted definition. We focus on studying only those hallucinations where a correct answer appears verbatim in the training set. We find that for a fixed dataset, larger and longer-trained LMs hallucinate less. While we see detector size improves performance on fixed LM's outputs, we find an inverse relationship between the scale of the LM and the detectability of its hallucinations.
  arXiv  Detail & Related papers  (2024-08-14T23:34:28Z)
• Self-Supervised Pretext Tasks for Alzheimer's Disease Classification using 3D Convolutional Neural Networks on Large-Scale Synthetic Neuroimaging Dataset [11.173478552040441]
  Alzheimer's Disease (AD) induces both localised and widespread neural degenerative changes throughout the brain. In this work, we evaluated several unsupervised methods to train a feature extractor for downstream AD vs. CN classification.
  arXiv  Detail & Related papers  (2024-06-20T11:26:32Z)
• Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models [68.91592125175787]
  Hallucinations pose a significant challenge for the practical implementation of large language models (LLMs) We present Rowen, a novel approach that enhances LLMs with a selective retrieval augmentation process tailored to address hallucinations.
  arXiv  Detail & Related papers  (2024-02-16T11:55:40Z)
• Reducing LLM Hallucinations using Epistemic Neural Networks [0.0]
  We train an ENN on top of the Llama-2 7B model combined with a contrastive decoding feature enhancement technique. We are the first to train an ENN for the next token prediction task and explore the efficacy of this method in reducing hallucinations on the TruthfulQA dataset.
  arXiv  Detail & Related papers  (2023-12-25T01:17:01Z)
• Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus [99.33091772494751]
  Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations. We propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs.
  arXiv  Detail & Related papers  (2023-11-22T08:39:17Z)
• HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data [102.56792377624927]
  hallucinations inherent in machine-generated data remain under-explored. We present a novel hallucination detection and elimination framework, HalluciDoctor, based on the cross-checking paradigm. Our method successfully mitigates 44.6% hallucinations relatively and maintains competitive performance compared to LLaVA.
  arXiv  Detail & Related papers  (2023-11-22T04:52:58Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection [63.56136319976554]
  Large Language Models (LLMs) generate hallucinations, which can cause significant damage when deployed for mission-critical tasks. We propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. We empirically evaluate our method and existing zero-resource detection methods on two datasets.
  arXiv  Detail & Related papers  (2023-10-10T10:14:59Z)
• A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation [76.34411067299331]
  Large language models often tend to 'hallucinate' which critically hampers their reliability. We propose an approach that actively detects and mitigates hallucinations during the generation process. We show that the proposed active detection and mitigation approach successfully reduces the hallucinations of the GPT-3.5 model from 47.5% to 14.5% on average.
  arXiv  Detail & Related papers  (2023-07-08T14:25:57Z)
• Contrastive Learning Reduces Hallucination in Conversations [76.55116206021346]
  We propose a contrastive learning scheme, named MixCL. A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs. We show that MixCL achieves comparable performance to state-of-the-art KB-based approaches.
  arXiv  Detail & Related papers  (2022-12-20T16:26:18Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)

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.