97 citations · 129 across the 41 of their papers we have counts for
8 papers · 1 filter
Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
Yanrui Du, Sendong Zhao, Ming Ma +2
Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious…
Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
Yanrui Du, Sendong Zhao, Haochun Wang +5
Explaining black-box model behavior with natural language has achieved impressive results in various NLP tasks. Recent research has explored the utilization of subsequences from th…
GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
Yanrui Du, Sendong Zhao, Yuhan Chen +5
Pre-trained models have achieved success in Chinese Short Text Matching (STM) tasks, but they often rely on superficial clues, leading to a lack of robust predictions. To address t…
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
Yuhan Chen, Nuwa Xi, Yanrui Du +4
Molecule discovery serves as a cornerstone in numerous scientific domains, fueling the development of new materials and innovative drug designs. Recent developments of in-silico mo…
Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
Yanrui Du, Sendong Zhao, Muzhen Cai +4
Extensive studies have been devoted to privatizing general-domain Large Language Models (LLMs) as Domain-Specific LLMs via feeding specific-domain data. However, these privatizatio…
UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language
Nuwa Xi, Sendong Zhao, Haochun Wang +3
Decoding text stimuli from cognitive signals (e.g. fMRI) enhances our understanding of the human language system, paving the way for building versatile Brain-Computer Interface. Ho…
Global Prompt Cell: A Portable Control Module for Effective Prompt Tuning
Chi Liu, Haochun Wang, Nuwa Xi +2
As a novel approach to tuning pre-trained models, prompt tuning involves freezing the parameters in downstream tasks while inserting trainable embeddings into inputs in the first l…
HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge
Haochun Wang, Chi Liu, Nuwa Xi +4
Large Language Models (LLMs), such as the LLaMA model, have demonstrated their effectiveness in various general-domain natural language processing (NLP) tasks. Nevertheless, LLMs h…