paper-with-me

홈 › Papers

Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection

2025-05-30 · YiXuan Wang, Shiqi Zhou, Chuanzhe Guo, Qingfu Zhu

Evol-Instruct has made significant improvements as a data synthesis method in several areas. Existing methods typically rely on a fixed set of strategies to evolve, which require manual design and are monolithic in form. In addition, iterative evolution also makes the acquisition of hard samples expensive. In view of this, we propose the Tag-Evol framework, a more diverse and efficient instruction evolving method. Specifically, Tag-Evol uses diverse and specific knowledge tags as strategies to achieve controlled evolution by injecting different combinations of tags into the original instructions. Experiments with multiple backbones in diverse domain benchmarks show that the proposed method generates significantly better evolved data than other methods. Furthermore, we conduct a thorough analysis of the evolved data, demonstrating that Tag-Evol is not only efficient but also generates more diverse and challenging data.

📄 PDF Abstract BibTeX arXiv:2505.24165

Code (1)

fghccv/tagevol 공식 구현

Tasks

TAG

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways

2025-05-30 · Kailin Jiang, Yuntao Du, Yukai Ding, Yuchen Ren 외

Large language/multimodal models (LLMs/LMMs) store extensive pre-trained knowledge but struggle to maintain consistency with real-world updates, making it difficult to avoid catastrophic forgetting while acquiring evolvi…

Continual LearningImage AugmentationInstruction Following

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

2026-02-23 · David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi, Maksym Andriushchenko arxiv

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instruc…

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections

2026-02-17 · Xianglin Yang, Yufei He, Shuo Ji, Bryan Hooi 외 arxiv

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external …

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

2026-06-10 · Pengfei He, Lesly Miculicich, Vishesh Sharma, Ash Fox 외 arxiv

Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted extern…

EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection

2025-05-20 · Yijie Lu, Tianjie Ju, Manman Zhao, Xinbei Ma 외

As multimodal agents are increasingly trained to operate graphical user interfaces (GUIs) to complete user tasks, they face a growing threat from indirect prompt injection, attacks in which misleading instructions are em…

Red Teaming