As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N=252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants' perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.

So this week, I wanted to give you guys something a little different. The weekly AI Disruption will continue next week. I hope this guide proves useful! One of the hottest topics in the field of AI right now is ChatGPT, short for chat-based Generative Pre-trained Transformer. This powerful tool is being used across industries and for many use cases.

The Keras Functional API provides a way to build flexible and complex neural networks in TensorFlow. The Functional API is used to design networks that are not linear. We used the Sequential API in the CNN tutorial to build an image classification model with Keras and TensorFlow. The Sequential API involves stacking layers. One layer is followed by another layer until the final dense layer.

They can translate images from one imaging modality to another at a low cost. For unpaired datasets, they rely mostly on cycle loss. Despite its effectiveness in learning the underlying data distribution, it can lead to a discrepancy between input and output data. The purpose of this work is to investigate the hypothesis that we can predict image quality based on its latent representation in the GANs bottleneck. We achieve this by corrupting the latent representation with noise and generating multiple outputs. The degree of differences between them is interpreted as the strength of the representation: the more robust the latent representation, the fewer changes in the output image the corruption causes. Our results demonstrate that our proposed method has the ability to i) predict uncertain parts of synthesized images, and ii) identify samples that may not be reliable for downstream tasks, e.g., liver segmentation task.

Starting from version 1.6, XGBoost has experimental support for multi-output regression and multi-label classification with Python package. Multi-label classification usually refers to targets that have multiple non-exclusive class labels. For instance, a movie can be simultaneously classified as both sci-fi and comedy. For detailed explanation of terminologies related to different multi-output models please refer to the scikit-learn user guide. Internally, XGBoost builds one model for each target similar to sklearn meta estimators, with the added benefit of reusing data and other integrated features like SHAP.

Neural networks play an important role in machine learning. Inspired by how human brains work, these computational systems learn a relationship between complex and often non-linear inputs and outputs. A basic neural network consists of an input layer, a hidden layer and an output layer. Each layer is made of a certain number of nodes or neurons. Neural networks with many layers are referred to as deep learning systems.

Conventional Bayesian Neural Networks (BNNs) are known to be capable of providing multiple outputs for a single input, the variations in which can be utilised to detect Out of Distribution (OOD) inputs. BNNs are difficult to train due to their sensitivity towards the choice of priors. To alleviate this issue, we propose pseudo-BNNs where instead of learning distributions over weights, we use point estimates and perturb weights at the time of inference. We modify the cost function of conventional BNNs and use it to learn parameters for the purpose of injecting right amount of random perturbations to each of the weights of a neural network with point estimate. In order to effectively segregate OOD inputs from In Distribution (ID) inputs using multiple outputs, we further propose two measures, derived from the index of dispersion and entropy of probability distributions, and combine them with the proposed pseudo-BNNs. Overall, this combination results in a principled technique to detect OOD samples at the time of inference. We evaluate our technique on a wide variety of neural network architectures and image classification datasets. We observe that our method achieves state of the art results and beats the related previous work on various metrics such as FPR at 95% TPR, AUROC, AUPR and Detection Error by just using 2 to 5 samples of weights per input.

When modelling censored observations, a typical approach in current regression methods is to use a censored-Gaussian (i.e. Tobit) model to describe the conditional output distribution. In this paper, as in the case of missing data, we argue that exploiting correlations between multiple outputs can enable models to better address the bias introduced by censored data. To do so, we introduce a heteroscedastic multi-output Gaussian process model which combines the non-parametric flexibility of GPs with the ability to leverage information from correlated outputs under input-dependent noise conditions. To address the resulting inference intractability, we further devise a variational bound to the marginal log-likelihood suitable for stochastic optimization. We empirically evaluate our model against other generative models for censored data on both synthetic and real world tasks and further show how it can be generalized to deal with arbitrary likelihood functions. Results show how the added flexibility allows our model to better estimate the underlying non-censored (i.e. true) process under potentially complex censoring dynamics.

Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other. A primary issue that arises in the context of MOD learning is that for any given input pattern there can be multiple correct output patterns. This changes the learning task from function approximation to relation approximation. Previous algorithms do not consider this problem, and thus cannot be readily applied to MOD problems. To perform MOD learning, we introduce the Hierarchical Multi-Output Nearest Neighbor model (HMONN) that employs a basic learning model for each output and a modified nearest neighbor approach to refine the initial results.

Recently there has been an increasing interest in methods that deal with multiple outputs. This has been motivated partly by frameworks like multitask learning, multisensor networks or structured output data. From a Gaussian processes perspective, the problem reduces to specifying an appropriate covariance function that, whilst being positive semi-definite, captures the dependencies between all the data points and across all the outputs. One approach to account for non-trivial correlations between outputs employs convolution processes. Under a latent function interpretation of the convolution transform we establish dependencies between output variables. The main drawbacks of this approach are the associated computational and storage demands. In this paper we address these issues. We present different sparse approximations for dependent output Gaussian processes constructed through the convolution formalism. We exploit the conditional independencies present naturally in the model. This leads to a form of the covariance similar in spirit to the so called PITC and FITC approximations for a single output. We show experimental results with synthetic and real data, in particular, we show results in pollution prediction, school exams score prediction and gene expression data.