Picture for Xue Jiang

Xue Jiang

PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding

Add code
Jul 03, 2024
Viaarxiv icon

ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets

Add code
Jul 03, 2024
Figure 1 for ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
Figure 2 for ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
Figure 3 for ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
Figure 4 for ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
Viaarxiv icon

IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization

Add code
Jul 03, 2024
Viaarxiv icon

Towards Vision-Language Geo-Foundation Model: A Survey

Add code
Jun 13, 2024
Viaarxiv icon

Negative Label Guided OOD Detection with Pretrained Vision-Language Models

Add code
Mar 29, 2024
Figure 1 for Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Figure 2 for Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Figure 3 for Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Figure 4 for Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Viaarxiv icon

SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation

Add code
Feb 29, 2024
Figure 1 for SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation
Figure 2 for SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation
Figure 3 for SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation
Figure 4 for SEED: Customize Large Language Models with Sample-Efficient Adaptation for Code Generation
Viaarxiv icon

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models

Add code
Feb 24, 2024
Figure 1 for Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Figure 2 for Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Figure 3 for Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Figure 4 for Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Viaarxiv icon

Exact Tensor Completion Powered by Arbitrary Linear Transforms

Add code
Feb 02, 2024
Viaarxiv icon

PACE: Improving Prompt with Actor-Critic Editing for Large Language Model

Add code
Aug 19, 2023
Figure 1 for PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
Figure 2 for PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
Figure 3 for PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
Figure 4 for PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
Viaarxiv icon

Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search

Add code
Aug 02, 2023
Figure 1 for Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search
Figure 2 for Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search
Figure 3 for Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search
Figure 4 for Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search
Viaarxiv icon