Papers by Tiejin Chen
Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for MAS fail to address the unique complexities of multi-step reasoning . Existing uncertainty quantification methods struggle with cascading uncertainty . |
| Approach: | They propose a framework that quantifies uncertainty through tensor decomposition . they show that MATU effectively estimates holistic and robust uncertainty . |
| Outcome: | The proposed framework disentangles and quantifies distinct sources of uncertainty . it is generalizable across different agent structures and can be used for scientific discovery, education, healthcare and transportation. |
Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Multi-modal large language models are highly vulnerable to jailbreak attacks due to their additional modality. |
| Approach: | They propose a black-box jailbreak framework based on zeroth-order optimization . they propose generating malicious images and patch-wise block coordinate descent . |
| Outcome: | The proposed framework achieves 98.2% success on MiniGPT-4 and 95% on the Harmful Behaviors Multi-modal dataset while jailbreaking commercial models such as GPT-4o. |
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. |
Uncertainty Quantification of Large Language Models through Multiple Uncertainty Sources (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for uncertainty quantification fail to capture multifaceted nature of natural language generation. |
| Approach: | They propose a multi-resource Uncertainty Quantification framework that integrates heterogeneous uncertainty signals into a unified measure. |
| Outcome: | The proposed framework outperforms existing methods on CoQA, NQ_Open, and HotpotQA. |
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing uncertainty-aware approaches weight preferences, but ignore reliability of the answers being compared. |
| Approach: | They propose a framework that grounds preference weighting in Conformal Predictions to address this problem. |
| Outcome: | The proposed framework improves alignment robustness and data efficiency across different datasets. |