Related papers: SALAD: Improving Robustness and Generalization thr…

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on…

Word alignment is an important natural language processing task that indicates the correspondence between natural languages. Recently, unsupervised learning of log-linear models for word alignment has received considerable attention as it…

Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made great progress in extracting personal signals from the query…

Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for…

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---while still failing on…

Pre-trained language models (PLMs) have achieved remarkable success on various natural language understanding tasks. Simple fine-tuning of PLMs, on the other hand, might be suboptimal for domain-specific tasks because they cannot possibly…

Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, and recent efforts have sought to extend their capabilities to multimodal domains and resource-constrained environments. However,…

To facilitate zero-shot generalization in taskoriented dialog, this paper proposes Language Models as Data (LAD). LAD is a paradigm for creating diverse and accurate synthetic data which conveys the necessary structural constraints and can…

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely…

We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal component analysis based feature-reconstruction error (fre) to…

Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…

The broad capabilities of Language Models (LMs) can be limited by their sensitivity to distractor tasks: LMs can infer secondary tasks from the prompt in addition to the intended one, leading to unwanted outputs. For example, prompt…

Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some…

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee on the downstream…

Many constructs that characterize language, like its complexity or emotionality, have a naturally continuous semantic structure; a public speech is not just "simple" or "complex," but exists on a continuum between extremes. Although large…

The current paradigm of evaluating Large Language Models (LLMs) through static benchmarks comes with significant limitations, such as vulnerability to data contamination and a lack of adaptability to the evolving capabilities of LLMs.…

Recent advances in large language model (LLM) training have highlighted the need for diverse, high-quality instruction data. Recently, many works are exploring synthetic data generation using LLMs. However, they primarily focus on prompt…