paper-with-me

홈 › Papers

A Two Stage Adaptation Framework for Frame Detection via Prompt Learning

2022-10-01 · COLING 2022 10 · Xinyi Mou, Zhongyu Wei, Changjian Jiang, Jiajie Peng

Framing is a communication strategy to bias discussion by selecting and emphasizing. Frame detection aims to automatically analyze framing strategy. Previous works on frame detection mainly focus on a single scenario or issue, ignoring the special characteristics of frame detection that new events emerge continuously and policy agenda changes dynamically. To better deal with various context and frame typologies across different issues, we propose a two-stage adaptation framework. In the framing domain adaptation from pre-training stage, we design two tasks based on pivots and prompts to learn a transferable encoder, verbalizer, and prompts. In the downstream scenario generalization stage, the transferable components are applied to new issues and label sets. Experiment results demonstrate the effectiveness of our framework in different scenarios. Also, it shows superiority both in full-resource and low-resource conditions.

📄 PDF Abstract BibTeX

Code (1)

xymou/frame_detection 공식 구현 pytorch

Tasks

Domain AdaptationPrompt LearningVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

Prompt-DAS: Annotation-Efficient Prompt Learning for Domain Adaptive Semantic Segmentation of Electron Microscopy Images

2025-09-23 · Jiabao Chen, Shan Xiong, Jialin Peng arxiv

Domain adaptive segmentation (DAS) of numerous organelle instances from large-scale electron microscopy (EM) is a promising way to enable annotation-efficient learning. Inspired by SAM, we propose a promptable multitask …

Unsupervised Domain AdaptationInteractive SegmentationSemantic SegmentationContrastive Learning

Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection

2024-09-30 · Yubin Wang, Zhikang Zou, Xiaoqing Ye, Xiao Tan 외

We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains. Due to substantial d…

Transfer-Prompting: Enhancing Cross-Task Adaptation in Large Language Models via Dual-Stage Prompts Optimization

2025-02-20 · Yupeng Chang, Yi Chang, Yuan Wu

Large language models (LLMs) face significant challenges when balancing multiple high-level objectives, such as generating coherent, relevant, and high-quality responses while maintaining efficient task adaptation across…

System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection

2025-12-10 · Binglin Wu, Jiaxiu Zou, Xianneng Li arxiv

The proliferation of hate speech on Chinese social media poses urgent societal risks, yet traditional systems struggle to decode context-dependent rhetorical strategies and evolving slang. To bridge this gap, we propose …

Hate Speech DetectionPrompt EngineeringDomain Adaptation

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

2026-06-12 · Tan Zhu, Tong Yao, Kananart Kuwaranancharoen, Amit Singh 외 arxiv

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is cr…

Prompt Engineering