Papers by Jiahui Yu
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Despite advances in training Large Language Models, they remain vulnerable to jailbreak, an adversarial attack method. |
| Approach: | They propose an adversarial jailbreak algorithm that exploits the gradient information of the suffix tokens to accelerate the optimization process. |
| Outcome: | The proposed model achieves 1.5x speedup while maintaining high attack success rates. |
CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models (2024.findings-acl)
Copied to clipboard
Linhao Yu, Yongqi Leng, Yufei Huang, Shang Wu, Haixin Liu, Xinmeng Ji, Jiahui Zhao, Jinwang Song, Tingting Cui, Xiaoqing Cheng, Liutao Liutao, Deyi Xiong
| Challenge: | Recent years have witnessed remarkable progress achieved by large language models in both natural language understanding and generation. |
| Approach: | They propose a large benchmark CMoralEval for moral evaluation of Chinese LLMs . they use a Chinese TV program discussing Chinese moral norms and Chinese moral anomies based on various sources . |
| Outcome: | The proposed dataset is characterized by diversity and authenticity. |
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)
Copied to clipboard
Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang
| Challenge: | Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences . |
| Approach: | They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification . |
| Outcome: | The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization. |
HyperHatePrompt: A Hypergraph-based Prompting Fusion Model for Multimodal Hate Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models for multimodal hate detection lack implicit hateful cues, cross-modal-induced hate, and diversity of hate target groups. |
| Approach: | They propose a hypergraph-based prompting fusion model that uses LLMs to generate hate cue prompts and hypergraph learning to merge multimodal hate features. |
| Outcome: | The proposed model outperforms state-of-the-art models on two benchmark datasets showing that it can detect hate content across multiple modalities. |
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)
Copied to clipboard
Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions . |
| Approach: | They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline . |
| Outcome: | The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy . |
PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing black-box fingerprinting techniques rely on overfitting high-perplexity trigger patterns . experimental results show that model editing in the fingerprint domain exhibits unique advantages . |
| Approach: | They propose a prefix-enhanced fingerprint editing framework that encodes copyright information into parameter offsets through dual-channel knowledge edit to achieve covert embedding of fingerprint features. |
| Outcome: | The proposed model editing framework achieves 90% trigger precision in mainstream architectures . the proposed model editor achieves the 90% accuracy in mainstream models . |
ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios. |
| Approach: | They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset. |
| Outcome: | The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation. |
Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment (2025.acl-long)
Copied to clipboard
Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James Kwok
| Challenge: | Recent studies show that reasoning abilities contribute significantly to model safety, while integrating Mixture-of-Experts (MoE) architectures can further enhance alignment. |
| Approach: | They propose a framework that synergistically combines reasoning chains and expert mixtures to improve self-alignment. |
| Outcome: | The proposed framework improves model safety, jailbreak resistance, and over-refusal capabilities, achieving performance comparable to OpenAI’s state-of-the-art o1 model. |
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work on dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). |
| Approach: | They propose a progressive zero-shot dataset generation framework which leverages feedback from the task-specific model to guide the generation of new training data via in-context examples. |
| Outcome: | The proposed framework achieves on-par or superior performance with only 1% synthetic dataset size, when compared to baseline methods without in-context feedback. |