Investigating the Security Threat Arising from "Yes-No" Implicit Bias in Large Language Models.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
Towards Secure Tuning: Mitigating Security Risks Arising from Benign Instruction Fine-Tuning.
CoRR, 2024
MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views.
CoRR, 2024
MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability.
CoRR, 2024
MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Probing the Dual Logic Ability of Privatized Medical-Domain LLMs.
Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2024
MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak.
CoRR, 2023
The CALLA Dataset: Probing LLMs' Interactive Knowledge Acquisition from Chinese Medical Literature.
CoRR, 2023
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese.
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue.
CoRR, 2023
Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation.
CoRR, 2022
Correction to: A method of VR‑EEG scene cognitive rehabilitation training.
Health Inf. Sci. Syst., 2021
A method of VR-EEG scene cognitive rehabilitation training.
Health Inf. Sci. Syst., 2021