Reducing LLM Hallucinations using Epistemic Neural Networks

• URL: http://arxiv.org/abs/2312.15576v1
• Date: Mon, 25 Dec 2023 01:17:01 GMT
• Title: Reducing LLM Hallucinations using Epistemic Neural Networks
• Authors: Shreyas Verma, Kien Tran, Yusuf Ali, Guangyu Min
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reducing and detecting hallucinations in large language models is an open research problem. In this project, we attempt to leverage recent advances in the field of uncertainty estimation to reduce hallucinations in frozen large language models. Epistemic neural networks have recently been proposed to improve output joint distributions for large pre-trained models. ENNs are small networks attached to large, frozen models to improve the model's joint distributions and uncertainty estimates. In this work, we train an epistemic neural network 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. In essence, we provide a method that leverages a pre-trained model's latent embeddings to reduce hallucinations.

Related papers

• Interpretable Language Modeling via Induction-head Ngram Models [74.26720927767398]
  We propose Induction-head ngram models (Induction-Gram) to bolster modern ngram models with a hand-engineered "induction head" This induction head uses a custom neural similarity metric to efficiently search the model's input context for potential next-word completions. Experiments show that this simple method significantly improves next-word prediction over baseline interpretable models.
  arXiv  Detail & Related papers  (2024-10-31T12:33:26Z)
• Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks [0.5827521884806072]
  Large neural networks trained on large datasets have become the dominant paradigm in machine learning. This thesis develops scalable methods to equip neural networks with model uncertainty.
  arXiv  Detail & Related papers  (2024-04-29T23:38:58Z)
• Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions [1.0499611180329804]
  Projection-based model order reduction has been recently proposed for problems with slowly decaying Kolmogorov n-width. A disadvantage of the previously proposed methods is the potential high computational costs of training the networks on high-fidelity solution snapshots. We propose and analyze a novel method that overcomes this disadvantage by training a neural network only on subsampled versions of the high-fidelity solution snapshots.
  arXiv  Detail & Related papers  (2023-03-16T20:18:33Z)
• Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean [1.0923877073891446]
  Deep neural networks (DNNs) have proven to be highly effective in a variety of tasks. Despite this success, the inner workings of DNNs are often not transparent. This lack of interpretability has led to increased research on inherently interpretable neural networks.
  arXiv  Detail & Related papers  (2023-01-27T17:06:13Z)
• NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration [66.22668336495175]
  A lack of consideration for neural network calibration will not gain trust from humans. We introduce the Neural Clamping Toolkit, the first open-source framework designed to help developers employ state-of-the-art model-agnostic calibrated models.
  arXiv  Detail & Related papers  (2022-11-29T15:03:05Z)
• Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration [62.4971588282174]
  We propose a new post-processing calibration method called Neural Clamping. Our empirical results show that Neural Clamping significantly outperforms state-of-the-art post-processing calibration methods.
  arXiv  Detail & Related papers  (2022-09-23T14:18:39Z)
• Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregation [0.0]
  convolutional neural networks (CNNs) have brought breakthroughs in processing clinical electrocardiograms (ECGs) and speaker-independent speech. In this paper, we propose local pattern aggregation-based deep-learning models to effectively deal with both problems. The novel network structure, called LPANet, has cropping and aggregation operations embedded into it.
  arXiv  Detail & Related papers  (2022-05-28T13:18:18Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• An alternative approach to train neural networks using monotone variational inequality [22.320632565424745]
  We propose an alternative approach to neural network training using the monotone vector field. Our approach can be used for more efficient fine-tuning of a pre-trained neural network.
  arXiv  Detail & Related papers  (2022-02-17T19:24:20Z)
• A Bayesian Perspective on Training Speed and Model Selection [51.15664724311443]
  We show that a measure of a model's training speed can be used to estimate its marginal likelihood. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. Our results suggest a promising new direction towards explaining why neural networks trained with gradient descent are biased towards functions that generalize well.
  arXiv  Detail & Related papers  (2020-10-27T17:56:14Z)
• Neural networks with late-phase weights [66.72777753269658]
  We show that the solutions found by SGD can be further improved by ensembling a subset of the weights in late stages of learning. At the end of learning, we obtain back a single model by taking a spatial average in weight space.
  arXiv  Detail & Related papers  (2020-07-25T13:23:37Z)

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.