相关论文: Interpretable Discriminative Text Representations …

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…

In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language…

Language Bottleneck Models (LBMs) are proposed to achieve interpretable image recognition by classifying images based on textual concept bottlenecks. However, current LBMs simply list all concepts together as the bottleneck layer, leading…

There is growing recognition that many NLP tasks lack a single ground truth, as human judgments reflect diverse perspectives. To capture this variation, models have been developed to predict full annotation distributions rather than…

Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for…

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a…

AI-generated text detection has attracted increasing attention as powerful language models approach human-level generation. Limited work is devoted to detecting (partially) AI-paraphrased texts. However, AI paraphrasing is commonly employed…

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction…

Detecting Alzheimer's Disease (AD) from narrative transcripts remains a challenging task for large language models (LLMs), particularly under out-of-distribution (OOD) and data-scarce conditions. While in-context learning (ICL) provides a…

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

In response to the rapid growth of Internet of Things (IoT) devices and rising security risks, Radio Frequency Fingerprint (RFF) has become key for device identification and authentication. However, various changing factors - beyond the RFF…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label…

This paper shows that a popular approach to the supervised embedding of documents for classification, namely, contrastive Word Mover's Embedding, can be significantly enhanced by adding interpretability. This interpretability is achieved by…

This paper introduces LAFT, a novel feature transformation method designed to incorporate user knowledge and preferences into anomaly detection using natural language. Accurately modeling the boundary of normality is crucial for…

We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled and locally fair representations. We learn a locally fair…

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…