Picture for Bairu Hou

Bairu Hou

A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation

Add code
Jun 11, 2024
Viaarxiv icon

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

Add code
Apr 18, 2024
Viaarxiv icon

A Survey on Data Selection for Language Models

Add code
Mar 08, 2024
Viaarxiv icon

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Add code
Feb 28, 2024
Figure 1 for Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Figure 2 for Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Figure 3 for Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Figure 4 for Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Viaarxiv icon

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

Add code
Nov 15, 2023
Viaarxiv icon

Certified Robustness for Large Language Models with Self-Denoising

Add code
Jul 14, 2023
Viaarxiv icon

Improving Diffusion Models for Scene Text Editing with Dual Encoders

Add code
Apr 12, 2023
Viaarxiv icon

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

Add code
Dec 19, 2022
Viaarxiv icon

TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

Add code
Dec 19, 2022
Viaarxiv icon

Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations

Add code
Sep 19, 2020
Figure 1 for Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Figure 2 for Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Figure 3 for Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Figure 4 for Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Viaarxiv icon