相关论文: Is Your Model Sensitive? SPeDaC: A New Benchmark f…

Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and…

Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to…

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for,…

Personas are useful for dialogue response prediction. However, the personas used in current studies are pre-defined and hard to obtain before a conversation. To tackle this issue, we study a new task, named Speaker Persona Detection (SPD),…

Multi-label sentiment classification plays a vital role in natural language processing by detecting multiple emotions within a single text. However, existing datasets like GoEmotions often suffer from severe class imbalance, which hampers…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition. This is because of the large…

Diagnosing autism spectrum disorder (ASD) by identifying abnormal speech patterns from examiner-patient dialogues presents significant challenges due to the subtle and diverse manifestations of speech-related symptoms in affected…

Metadata are associated to most of the information we produce in our daily interactions and communication in the digital world. Yet, surprisingly, metadata are often still catergorized as non-sensitive. Indeed, in the past, researchers and…

In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks. To evaluate the knowledge ability of language models, previous studies have…

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that…

Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale. The de-facto method in this type of black-box…

Semi-supervised domain adaptation (SSDA) presents a critical hurdle in computer vision, especially given the frequent scarcity of labeled data in real-world settings. This scarcity often causes foundation models, trained on extensive…

Nowadays, topic classification from tweets attracts considerable research attention. Different classification systems have been suggested thanks to these research efforts. Nevertheless, they face major challenges owing to low performance…

Detecting out-of-distribution (OOD) data is a task that is receiving an increasing amount of research attention in the domain of deep learning for computer vision. However, the performance of detection methods is generally evaluated on the…

In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, under mild assumptions on the data, provably achieves…

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…

Domain classification is the task of mapping spoken language utterances to one of the natural language understanding domains in intelligent personal digital assistants (IPDAs). This is a major component in mainstream IPDAs in industry.…

Modeling human personality is important for several AI challenges, from the engineering of artificial psychotherapists to the design of persona bots. However, the field of computational personality analysis heavily relies on labeled data,…