Papers by Pingzhi Li

6 papers
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges (2025.findings-acl)

Copied to clipboard

Challenge: Privacy risks in text-only Large Language Models are well-documented, especially their tendency to memorize and leak sensitive information.
Approach: They propose a dataset to assess privacy risks across multi-modal tasks and scenarios . they demonstrate how models leak sensitive data across various tasks .
Outcome: The proposed model can leak sensitive data embedded in images or stored in memory, exposing privacy risks.
Vision Language Model Helps Private Information De-Identification in Vision Data (2025.findings-acl)

Copied to clipboard

Challenge: Visual Language Models (VLMs) have gained popularity due to their ability to solve imagerelated tasks.
Approach: They propose a framework to enhance privacy awareness of visual language models . they use a specialized instruction-tuning dataset and a tailored training methodology .
Outcome: The proposed framework outperforms existing approaches in handling private information.
Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design (2025.naacl-long)

Copied to clipboard

Challenge: Using Mixture-of-Experts, researchers have found that efficient MoE is difficult to achieve due to two key reasons: imbalanced expert activation and massive communication overhead.
Approach: They propose a collaboration-constrained routing strategy that encourages more specialized expert groups and leverages expert specialization.
Outcome: The proposed approach achieves an average performance improvement of 0.51% and 0.33% on LLaMA-MoE and Qwen-MaE respectively.
Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on isolated aspects of MoE, with conflicting conclusions . a lack of consensus on optimal design choices is limiting to specific aspects of the model.
Approach: They propose to evaluate two popular MoE backbones across four dimensions of design choices . they find token-level routing and z-loss regularization improve reasoning performance .
Outcome: The proposed framework evaluates two popular MoE backbones on over eight metrics.
ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to low-rank Adaptation (LoRA) are limited in scalability and controllability.
Approach: They propose a conditional recurrent diffusion framework that generates LoRA parameters directly . they integrate model architecture and textual task specifications to generate task-specific parameters .
Outcome: The proposed framework scales to billions-of-parameter LLMs and maintains controllability.
Glider: Global and Local Instruction-Driven Expert Router (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for routing-based expert models favor generalization over performance on held-in tasks.
Approach: They propose a global and local instruction driven expert router that leverages recent LLMs' semantic reasoning capabilities to generate task-specific instructions from the input query.
Outcome: The proposed method improves held-in performance while maintaining strong generalization on held-out tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations