Related papers: CREST: A Joint Framework for Rationalization and C…

As real-world knowledge evolves, the information embedded within large language models (LLMs) can become outdated, inadequate, or erroneous. Model editing has emerged as a prominent approach for updating LLMs' knowledge with minimal…

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with human reasoning.…

Recent work on language model self-improvement shows that models can refine their own reasoning through reflection, verification, debate, or self-generated rewards. However, most existing approaches rely on external critics, learned reward…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

In many settings it is important for one to be able to understand why a model made a particular prediction. In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet…

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as…

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

The aim of Logic2Text is to generate controllable and faithful texts conditioned on tables and logical forms, which not only requires a deep understanding of the tables and logical forms, but also warrants symbolic reasoning over the…

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on…

Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization…

Learning representations of stochastic processes is an emerging problem in machine learning with applications from meta-learning to physical object models to time series. Typical methods rely on exact reconstruction of observations, but…

(Natural Language Processing) NLP techniques such as text classification and topic discovery are very useful in many application areas including information retrieval, knowledge discovery, policy formulation, and decision-making. However,…

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as…

Counterfactual explanations can be used to interpret and debug text classifiers by producing minimally altered text inputs that change a classifier's output. In this work, we evaluate five methods for generating counterfactual explanations…

Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generation is hindered by a non-uniform usage of data sets and…

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the…

Specialist language models (LMs) focus on a specific task or domain on which they often outperform generalist LMs of the same size. However, the specialist data needed to pretrain these models is only available in limited amount for most…