Related papers: Automated Essay Scoring based on Two-Stage Learnin…

Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of…

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.…

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

Evaluating Text Style Transfer (TST) is a complex task due to its multifaceted nature. The quality of the generated text is measured based on challenging factors, such as style transfer accuracy, content preservation, and overall fluency.…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e.,…

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

In the prompt-specific holistic score prediction task for Automatic Essay Scoring, the general approaches include pre-trained neural model, coherence model, and hybrid model that incorporate syntactic features with neural model. In this…

We show how to obtain improved active learning methods in the agnostic (adversarial noise) setting by combining marginal leverage score sampling with non-independent sampling strategies that promote spatial coverage. In particular, we…

In this work, we present an approach based on combining string kernels and word embeddings for automatic essay scoring. String kernels capture the similarity among strings based on counting common character n-grams, which are a low-level…

In this paper we determine how multi-layer ensembling improves performance on multilingual intent classification. We develop a novel multi-layer ensembling approach that ensembles both different model initializations and different model…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

To simplify the generation process, several text-to-speech (TTS) systems implicitly learn intermediate latent representations instead of relying on predefined features (e.g., mel-spectrogram). However, their generation quality is…

Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent dynamic benchmarks can alleviate staleness they often increase difficulty at the expense…

Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performance of downstream tasks, such as intent detection and slot…

Large language models (LLMs) have achieved strong performance on reasoning benchmarks, yet their ability to solve real-world problems requiring end-to-end workflows remains unclear. Mathematical modeling competitions provide a stringent…

We give a new consistent scoring function for structure learning of Bayesian networks. In contrast to traditional approaches to score-based structure learning, such as BDeu or MDL, the complexity penalty that we propose is data-dependent…

This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL): robustness against Byzantine attacks, fairness, and privacy preservation. To improve the system's defense against…