Related papers: Structured Prompt Optimization for Few-Shot Text C…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks are essential for guiding deployment decisions. In practice, however, frameworks such as Holistic Evaluation of Language Models (HELM)…

Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature, recent research attempted to integrate the powerful pretrained models into…

Few-shot named entity recognition (NER) targets generalizing to unseen labels and/or domains with few labeled examples. Existing metric learning methods compute token-level similarities between query and support sets, but are not able to…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured…

The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring `prompt engineering'. To harness visual concepts from target images without prompt…

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of…

Recent advances for few-shot text classification aim to wrap textual inputs with task-specific prompts to cloze questions. By processing them with a masked language model to predict the masked tokens and using a verbalizer that constructs…

The Segment Anything Model (SAM) has demonstrated impressive generalization in prompt-based segmentation. Yet, the potential of semantic text prompts remains underexplored compared to traditional spatial prompts like points and boxes. This…

Synthetic data has become a cornerstone for scaling large language models, yet its multilingual use remains bottlenecked by translation-based prompts. This strategy inherits English-centric framing and style and neglects cultural…

Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…

Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely…

In large-scale industrial LLM systems, prompt templates often expand to thousands of tokens as teams iteratively incorporate sections such as task instructions, few-shot examples, and heuristic rules to enhance robustness and coverage. This…

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success,…

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods…

In this paper, we explore how to utilize pre-trained language model to perform few-shot text classification where only a few annotated examples are given for each class. Since using traditional cross-entropy loss to fine-tune language model…

Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and…