2025, Zizhong Li, Haopeng Zhang, Jiawei Zhang
This paper proposes Token-level Precise Attack on the RAG (TPARAG), which leverages a lightweight white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level and is suitable for both white-box and black-box RAG systems.
2024, Zizhong Li, Haopeng Zhang, Jiawei Zhang
This paper introduce Intermediate Distillation, a data-efficient knowledge distillation training scheme that treats LLMs as black boxes and distills their knowledge via an innovative LLM-ranker-retriever pipeline, solely using LLMs ranking generation as the supervision signal.
2024, Zizhong Li, Haopeng Zhang, Jiawei Zhang
This paper conducts a comprehensive review of attention distillation workflow and identifying key factors influencing the learning quality of retrieval-augmented language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics.
2023, Zizhong Li, Haopeng Zhang, Jiawei Zhang
This paper revisits the existing fake news dataset verified by human journalists with augmented fact-checking by large language models (ChatGPT), and we name the augmented fake news dataset ChatGPT-FC.