paper-with-me

홈 › Papers

Learning Label Modular Prompts for Text Classification in the Wild

2022-11-30 · Hailin Chen, Amrita Saha, Shafiq Joty, Steven C. H. Hoi

Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in-the-wild, which introduces different non-stationary training/testing stages. Decomposing a complex task into modular components can enable robust generalisation under such non-stationary environment. However, current modular approaches in NLP do not take advantage of recent advances in parameter efficient tuning of pretrained language models. To close this gap, we propose MODULARPROMPT, a label-modular prompt tuning framework for text classification tasks. In MODULARPROMPT, the input prompt consists of a sequence of soft label prompts, each encoding modular knowledge related to the corresponding class label. In two of most formidable settings, MODULARPROMPT outperforms relevant baselines by a large margin demonstrating strong generalisation ability. We also conduct comprehensive analysis to validate whether the learned prompts satisfy properties of a modular representation.

📄 PDF Abstract BibTeX arXiv:2211.17142

Code (1)

salesforce/ModularPrompt 공식 구현 pytorch

Tasks

text-classificationText Classification

Similar Papers 제목 키워드 기반

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

2024-09-13 · Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru, Oriol Nieto 외

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language promp…

Audio ClassificationDescriptiveText RetrievalZero-shot Audio Classification

Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation

2024-07-08 · Jian Qian, Miao Sun, Sifan Zhou, Ziyu Zhao 외

In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitabl…

DiversityIn-Context Learning

Real-Time Wildfire Localization on the NASA Autonomous Modular Sensor using Deep Learning

2026-01-20 · Yajvan Ravan, Aref Malek, Chester Dolph, Nikhil Behari arxiv

High-altitude, multi-spectral, aerial imagery is scarce and expensive to acquire, yet it is necessary for algorithmic advances and application of machine learning models to high-impact problems such as wildfire detection…

Image Classification

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

2026-05-28 · Ihor Stepanov, Aleksandr Smechov arxiv

Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak attempts, and unsafe responses without the cost profile of large guard…

Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation

2026-06-27 · Ananto Nayan Bala, Faisal Muhammad Shah arxiv

Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost. The benchmark introduced here …