Search Results for author:
Found 8 papers, 5 papers with code
MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
The agent accentuates task-relevant features in the molecular representation by understanding the natural language description of the task, just as a tailor customizes clothes for clients.
Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
The jailbreak idea of our method is "Inherent Response Tendency Analysis" which identifies real-world instructions that can inherently induce LLMs to generate affirmation responses and the corresponding jailbreak strategy is "Real-World Instructions-Driven Jailbreak" which involves strategically splicing real-world instructions identified through the above analysis around the malicious instruction.
Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
Through extensive experiments on five reasoning datasets from the ERASER benchmark, we demonstrate that our framework not only establishes a more reliable link between the generated rationale and model decision but also achieves competitive results in task performance and the quality of rationale.
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
Furthermore, our method shows a sustained improvement as the volume of pseudo data increases, revealing the great potential of pseudo data in advancing low-resource cross-modal molecule discovery.
Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
To address this challenge, we propose knowledge-tuning, which leverages structured medical knowledge bases for the LLMs to grasp domain knowledge efficiently and facilitate reliable response generation.
Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
We conduct several experiments to analyze the dual logic ability of LLMs by examining the consistency of the stance in responses to paired questions about the same fact.
GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
To address this issue, it is crucial to analyze and mitigate the influence of superficial clues on STM models.
Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation
In this study, we focus on the spurious correlation between word features and labels that models learn from the biased data distribution of training data.
