Papers by Peijie Jiang

8 papers
VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable.
Approach: They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns .
Outcome: The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC).
Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies have focused mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an original correct answer when confronted with misleading information.
Approach: They propose a two-stage evaluation pipeline to quantify the response uncertainty phenomenon by eliciting each model’s original response on unperturbed inputs and injecting explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions.
Outcome: The proposed model overturns a correct answer in 65% of cases after receiving a single deceptive cue.
A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging (2021.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that joint models of word segmentation and POS tagging can lead to better performance because they are closely related.
Approach: They propose a domain adaption method for Chinese word segmentation and POS tagging that uses a simple metric to model the gaps between target and target domains.
Outcome: The proposed method can gain significant performance improvements over baselines on a benchmark dataset.
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling (2022.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that Boundary-Aware BERT can improve Chinese sequence labeling tasks.
Approach: They propose to encode boundary information directly into pre-trained language models . they propose to use unsupervised boundary information instead of supervised boundary info .
Outcome: The proposed architecture improves Chinese sequence labeling tasks on ten benchmarks.
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design (2026.acl-industry)

Copied to clipboard

Challenge: a novel extension of neural scaling laws to Mixture-of-Experts models is proposed . a ratio of expert-attention compute is crucial for efficient MoE models .
Approach: They propose an extension of neural scaling laws to Mixture-of-Experts (MoE) models . they define the ratio r as the fraction of total FLOPs per token dedicated to expert and attention layers .
Outcome: The proposed model can be tuned beyond size and data with the proposed model.
Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis (2025.acl-long)

Copied to clipboard

Challenge: Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE architectures.
Approach: They propose to analyze sparse MoE architectures against dense models to capture dynamic routing-expert interactions.
Outcome: The proposed algorithm shows that sparse models achieve higher efficiency per layer . it also shows that deep Qwen-MoE mitigates expert failures while minimizing complexity .
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say .
Approach: They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning.
Outcome: The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation .
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs.
Approach: They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility .
Outcome: The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility.

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