Papers by Ziqian Wang

10 papers
Adaptive Policy with Wait-k Model for Simultaneous Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to simultaneous machine translation require a robust read/write policy . a standalone multi-path wait-k model performs competitively with adaptive policies .
Approach: They propose a more flexible approach by decoupling the adaptive policy model from the translation model.
Outcome: The proposed approach outperforms baseline approaches in translation tasks.
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)

Copied to clipboard

Challenge: Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead.
Approach: They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type .
Outcome: The proposed method can prevent the linear growth of the privacy budget.
Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator (2024.lrec-main)

Copied to clipboard

Challenge: Recent work proposed to use a pre-trained textual entailment model for event detection . but, those methods treated the TE model as a frozen annotator .
Approach: They propose to use TE models to annotate large-scale unlabeled text and annotated data to fine-tune the TE model.
Outcome: The proposed method outperforms baseline methods by 15% on the ACE05 dataset.
Gradient-Guided Multi-Judge Prompt Optimization (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to prompt optimization trade off signal quality against computational cost.
Approach: They propose a framework that uses a first-order gradient approximation to score segment importance in a continuous masking direction.
Outcome: The proposed framework improves efficiency and robustness by using a first-order gradient approximation to score segment importance in a continuous masking direction.
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)

Copied to clipboard

Challenge: Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns.
Approach: They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Outcome: The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach: They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome: The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach: They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome: The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.
On the Use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing zero-shot methods for information extraction use large amounts of gold standard data.
Approach: They propose a framework to utilize silver data to enhance zero-shot classification methods . they propose to use off-the-shelf models of other NLP tasks to perform inference on test data .
Outcome: The proposed framework outperforms baseline methods on TACRED and Wiki80 datasets by 5% and 6% on the zero-shot relation classification task and by 3% 7 % on Smile (Korean and Polish)
PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods evaluate candidate prompts by sampling full outputs, often coupled with self critique or human annotated preferences, which limits scalability, especially for smaller models or models that are not instruction tuned.
Approach: They propose a framework that uses token level cross entropy as a direct, lightweight evaluation signal to evaluate candidate prompts.
Outcome: The proposed framework outperforms prior prompt optimizers across model sizes and datasets.
Activation-Guided Local Editing for Jailbreaking Attacks (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for jailbreaking Large Language Models (LLMs) are limited and produce incoherent or unreadable inputs.
Approach: They propose a two-stage framework that performs a one-shot, scenario-based generation of context and rephrases the original malicious query to obscure its harmful intent.
Outcome: The proposed framework achieves state-of-the-art Attack Success Rate, with gains of up to 37.74% over the strongest baseline, and excellent transferability to black-box and large-scale models.

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