Limits for Learning with Language Models

With the advent of large language models (LLMs), the trend in NLP has been to train LLMs on vast amounts of data to solve diverse language understanding and generation tasks. The list of LLM successes is long and varied. Nevertheless, several recent papers provide empirical evidence that LLMs fail to capture important aspects of linguistic meaning. Focusing on universal quantification, we provide a theoretical foundation for these empirical findings by proving that LLMs cannot learn certain fundamental semantic properties including semantic entailment and consistency as they are defined in formal semantics. More generally, we show that LLMs are unable to learn concepts beyond the first level of the Borel Hierarchy, which imposes severe limits on the ability of LMs, both large and small, to capture many aspects of linguistic meaning. This means that LLMs will continue to operate without formal guarantees on tasks that require entailments and deep linguistic understanding.

Analyzing Semantic Faithfulness of Language Models via Input Intervention on Conversational Question Answering

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we generate adversarial examples for object detection, which entails detecting bounding boxes around multiple objects present in the image and classifying them at the same time, making it a harder task than against image classification. We specifically aim to attack the widely used Faster R-CNN by changing the predicted label for a particular object in an image: where prior work has targeted one specific object (a stop sign), we generalise to arbitrary objects, with the key challenge being the need to change the labels of all bounding boxes for all instances of that object type. To do so, we propose a novel method, named Pick-Object-Attack. Pick-Object-Attack successfully adds perturbations only to bounding boxes for the targeted object, preserving the labels of other detected objects in the image. In terms of perceptibility, the perturbations induced by the method are very small. Furthermore, for the first time, we examine the effect of adversarial attacks on object detection in terms of a downstream task, image captioning; we show that where a method that can modify all object types leads to very obvious changes in captions, the changes from our constrained attack are much less apparent.

Invariance-based Adversarial Attack on Neural Machine Translation Systems

Recently, NLP models have been shown to be susceptible to adversarial attacks. In this paper, we explore adversarial attacks on neural machine translation (NMT) systems. Given a sentence in the source language, the goal of the proposed attack is to change multiple words while ensuring that the predicted translation remains unchanged. In order to choose the word from the source vocabulary, we propose a soft-attention based technique. The experiments are conducted on two language pairs: English-German (en-de) and English-French (en-fr) and two state-of-the-art NMT systems: BLSTM-based encoder-decoder with attention and Transformer. The proposed soft-attention based technique outperforms existing methods like HotFlip by a significant margin for all the conducted experiments The results demonstrate that state-of-the-art NMT systems are unable to capture the semantics of the source language.

Mimic and Fool: A Task Agnostic Adversarial Attack

At present, adversarial attacks are designed in a task-specific fashion. However, for downstream computer vision tasks such as image captioning, image segmentation etc., the current deep learning systems use an image classifier like VGG16, ResNet50, Inception-v3 etc. as a feature extractor. Keeping this in mind, we propose Mimic and Fool, a task agnostic adversarial attack. Given a feature extractor, the proposed attack finds an adversarial image which can mimic the image feature of the original image. This ensures that the two images give the same (or similar) output regardless of the task. We randomly select 1000 MSCOCO validation images for experimentation. We perform experiments on two image captioning models, Show and Tell, Show Attend and Tell and one VQA model, namely, end-to-end neural module network (N2NMN). The proposed attack achieves success rate of 74.0%, 81.0% and 89.6% for Show and Tell, Show Attend and Tell and N2NMN respectively. We also propose a slight modification to our attack to generate natural-looking adversarial images. In addition, it is shown that the proposed attack also works for invertible architecture. Since Mimic and Fool only requires information about the feature extractor of the model, it can be considered as a gray-box attack.

A Limitation of V-Matrix based Methods

To estimate the conditional probability functions based on the direct problem setting, V-matrix based method was proposed. We construct V-matrix based constrained quadratic programming problems for which the inequality constraints are inconsistent. In particular, we would like to present that the constrained quadratic optimization problem for conditional probability estimation using V-matrix method may not have a consistent solution always.

CapsDeMM: Capsule network for Detection of Munro's Microabscess in skin biopsy images

This paper presents an approach for automatic detection of Munro's Microabscess in stratum corneum (SC) of human skin biopsy in order to realize a machine assisted diagnosis of Psoriasis. The challenge of detecting neutrophils in presence of nucleated cells is solved using the recent advances of deep learning algorithms. Separation of SC layer, extraction of patches from the layer followed by classification of patches with respect to presence or absence of neutrophils form the basis of the overall approach which is effected through an integration of a U-Net based segmentation network and a capsule network for classification. The novel design of the present capsule net leads to a drastic reduction in the number of parameters without any noticeable compromise in the overall performance. The research further addresses the challenge of dealing with Mega-pixel images (in 10X) vis-a-vis Giga-pixel ones (in 40X). The promising result coming out of an experiment on a dataset consisting of 273 real-life images shows that a practical system is possible based on the present research. The implementation of our system is available at https://github.com/Anabik/CapsDeMM.