Related papers: Counterfactual Variable Control for Robust and Int…

The imminent need to interpret the output of a Machine Learning model with counterfactual (CF) explanations - via small perturbations to the input - has been notable in the research community. Although the variety of CF examples is…

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the…

Canonical Correlation Analysis (CCA) is a multivariate technique that takes two datasets and forms the most highly correlated possible pairs of linear combinations between them. Each subsequent pair of linear combinations is orthogonal to…

Current textual question answering models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns in the data, so they fail to generalize to out-of-distribution settings. To make a more robust…

Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. However, excessive reliance on chain-of-thought (CoT) reasoning…

In this paper, we study the possibility of almost unsupervised Multiple Choices Question Answering (MCQA). Starting from very basic knowledge, MCQA model knows that some choices have higher probabilities of being correct than the others.…

In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choosing appropriate actions. The system is designed using an…

Counterfactual explanations are one of the most popular methods to make predictions of black box machine learning models interpretable by providing explanations in the form of `what-if scenarios'. Most current approaches optimize a…

Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e.g., a…

Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging…

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the…

Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with. To understand and better measure the…

Open-domain question answering (QA) is known to involve several underlying knowledge and reasoning challenges, but are models actually learning such knowledge when trained on benchmark tasks? To investigate this, we introduce several new…

Most works on modeling the conversation history in Conversational Question Answering (CQA) report a single main result on a common CQA benchmark. While existing models show impressive results on CQA leaderboards, it remains unclear whether…

We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. Deep Neural Networks with Controllable Rule Representations (DeepCTRL) incorporates a rule…

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Cross-validation (CV) is a popular method for model-selection. Unfortunately, it is not immediately obvious how to apply CV to unsupervised or exploratory contexts. This thesis discusses some extensions of cross-validation to unsupervised…

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal…

Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically training a surrogate model…

Fact-based Visual Question Answering (FVQA) requires external knowledge beyond visible content to answer questions about an image, which is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is…