相关论文: Global-to-Local Support Spectrums for Language Mod…

A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and cast interpretability as a statistical inference problem. We…

Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable,…

Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are…

The use of deep neural networks to make high risk decisions creates a need for global and local explanations so that users and experts have confidence in the modeling algorithms. We introduce a novel technique to find global and local…

Set-valued classification, a new classification paradigm that aims to identify all the plausible classes that an observation belongs to, can be obtained by learning the acceptance regions for all classes. Many existing set-valued…

Explanations are well-known to improve recommender systems' transparency. These explanations may be local, explaining an individual recommendation, or global, explaining the recommender model in general. Despite their widespread use, there…

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how reliably a model maps its stated reasons to its reported predictions by approximating a…

User acceptance of artificial intelligence agents might depend on their ability to explain their reasoning, which requires adding an interpretability layer that fa- cilitates users to understand their behavior. This paper focuses on adding…

Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small…

Prompt engineering for large language models is challenging, as even small prompt perturbations or model changes can significantly impact the generated output texts. Existing evaluation methods of LLM outputs, either automated metrics or…

Deep learning models have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Nevertheless, they are consistently utilized in many applications, consequential to…

This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are…

Users of social platforms often perceive these sites as supportive spaces to post about their mental health issues. Those conversations contain important traces about individuals' health risks. Recently, researchers have exploited this…

With the ever-increasing use of complex machine learning models in critical applications within the finance domain, explaining the decisions of the model has become a necessity. With applications spanning from credit scoring to credit…

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

Graphical models capture relations between entities in a wide range of applications including social networks, biology, and natural language processing, among others. Graph neural networks (GNN) are neural models that operate over graphs,…

Intent classification is crucial for conversational agents (chatbots), and deep learning models perform well in this area. However, little research has been done on the explainability of intent classification due to the absence of suitable…

We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting…

The recycling of contrastive language-image pre-trained (CLIP) models as backbones for a large number of downstream tasks calls for a thorough analysis of their transferability implications, especially their well-documented reproduction of…