paper-with-me

홈 › Papers

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

2023-11-18 · Doyoung Kim, Susik Yoon, Dongmin Park, YoungJun Lee, Hwanjun Song, Jihwan Bang, Jae-Gil Lee

In real-world continual learning (CL) scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies which are tailored to only handle semantic shifts of uniform degree (i.e., uniformly mild or uniformly abrupt). To address this limitation, we propose an adaptive prompting approach that effectively accommodates semantic shifts of varying degree where mild and abrupt shifts are mixed. AdaPromptCL employs the assign-and-refine semantic grouping mechanism that dynamically manages prompt groups in accordance with the semantic similarity between tasks, enhancing the quality of grouping through continuous refinement. Our experiment results demonstrate that AdaPromptCL outperforms existing prompting methods by up to 21.3%, especially in the benchmark datasets with diverse semantic shifts between tasks.

📄 PDF Abstract BibTeX arXiv:2311.12048

Code (1)

kaist-dmlab/adapromptcl 공식 구현 pytorch

Tasks

AllContinual LearningManagementSemantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptation

2024-04-23 · Yuxiang Yang, Lu Wen, Yuanyuan Xu, Jiliu Zhou 외

Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target …

Domain AdaptationPrompt Learning

AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning

2025-12-20 · Fei Song, Yi Li, Jiangmeng Li, Rui Wang 외 arxiv

Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Existing multi-prompt learning methods prima…

Ensemble Learning

Adaptive Semantic Prompt Caching with VectorQ

2025-02-06 · Luis Gaspar Schroeder, Shu Liu, Alejandro Cuadron, Mark Zhao 외

Semantic prompt caches reduce the latency and cost of large language model (LLM) inference by reusing cached LLM-generated responses for semantically similar prompts. Vector similarity metrics assign a numerical score to…

Language ModelingLanguage ModellingLarge Language Model

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

2026-05-20 · Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty arxiv

Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but ea…

Task-Adaptive Semantic Communications with Controllable Diffusion-based Data Regeneration

2025-05-12 · Fupei Guo, Achintha Wijesinghe, Songyang Zhang, Zhi Ding

Semantic communications represent a new paradigm of next-generation networking that shifts bit-wise data delivery to conveying the semantic meanings for bandwidth efficiency. To effectively accommodate various potential …

Semantic Communication