Papers by Siyuan Cheng

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models (2024.findings-emnlp)

Copied to clipboard

Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, Ningyu Zhang

Challenge:	Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately.
Approach:	They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains .
Outcome:	The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs.

MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)

Copied to clipboard

Jiaqi Li, Miaozeng Du, Chuanyi Zhang, Yongrui Chen, Nan Hu, Guilin Qi, Haiyun Jiang, Siyuan Cheng, Bozhong Tian

Multimodality

Challenge:	Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored.
Approach:	They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing.
Outcome:	The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs.

Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning (2023.findings-emnlp)

Copied to clipboard

Qingbin Liu, Yin Kung, Yanchao Hao, Dianbo Sui, Siyuan Cheng, Xi Chen, Ningyu Zhang, Jiaoyan Chen

Low-Resource NLP

Challenge:	Existing approaches to relation extraction can only recognize predefined relation types . new or out-of-scope relation types may continually emerge after the model is deployed .
Approach:	They propose a novel relation detection task that uses self-supervised learning to handle shallow semantic similarity problem.
Outcome:	The proposed method outperforms state-of-the-art methods on two datasets.

System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)

Copied to clipboard

Lu Yan, Siyuan Cheng, Xuan Chen, Kaiyuan Zhang, Guangyu Shen, Xiangyu Zhang

Responsible & Trustworthy NLP

Challenge:	Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training.
Approach:	They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack .
Outcome:	The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations.

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction (2025.emnlp-main)

Copied to clipboard

Chang Su, Dengliang Shi, Siyuan Huang, Jintao Du, Changhua Meng, Yu Cheng, Weiqiang Wang, Zhouhan Lin

Semantic Text Processing

Challenge:	Existing text embedding approaches often leverage the embeddment of the final token, typically a reserved special token such as ‘[EOS]‘.
Approach:	They propose to add a new training stage before contrastive learning to enrich the semantics of the final token embedding.
Outcome:	The proposed training stage improves performance on the Massive Text Embedding Benchmark (MTEB), achieving new state-of-the-art results across different LLM base models and scales.

Can We Edit Multimodal Large Language Models? (2023.emnlp-main)

Copied to clipboard

Siyuan Cheng, Bozhong Tian, Qingbin Liu, Xi Chen, Yongheng Wang, Huajun Chen, Ningyu Zhang

Semantic Text Processing

Challenge:	Existing methods to edit multimodal models have been used to incrementally infuse a language model with a new set of facts.
Approach:	They construct a benchmark for editing multimodal Large Language Models and establish metrics for evaluation.
Outcome:	The proposed benchmarks show that editing multimodal models is not as difficult as editing single-modal models.

Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)

Copied to clipboard

Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang

Language Models

Challenge:	Recent advances in model editing for LLMs have created challenges and opportunities for the community.
Approach:	They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.
Outcome:	The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (2024.acl-demos)

Copied to clipboard

Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen

Language Models

Challenge:	Large Language Models (LLMs) suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.
Approach:	They propose an easy-to-use knowledge editing framework for Large Language Models that allows users to easily edit updated knowledge and adjust undesired behavior while minimizing the impact on unrelated inputs.
Outcome:	The proposed framework surpasses traditional fine-tuning in terms of reliability and generalization.

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection (2026.findings-acl)

Copied to clipboard

Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei

Responsible & Trustworthy NLP

Challenge:	Existing reasoning models are limited by inefficiency and computational redundancy . PRISM-MCTS integrates a process reward model with a dynamic shared memory .
Approach:	They propose a reasoning framework that integrates a process reward model with a dynamic shared memory.
Outcome:	PRISM-MCTS integrates a process reward model with a dynamic shared memory . it halves trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1 .

Contrastive Demonstration Tuning for Pre-trained Language Models (2022.findings-emnlp)

Copied to clipboard

Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng, Zhenru Zhang, Chuanqi Tan, Huajun Chen

Language Models

Challenge:	Recent studies focus on searching discrete or continuous prompts or optimized verbalizers, yet the demonstration examples are crucial for an excellent final performance of prompt-tuning.
Approach:	They propose a pluggable, extensible, and efficient approach to prompt tuning that is free of demonstration sampling.
Outcome:	The proposed approach can be pluggable, extensible, and efficient on 16 datasets.

Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis (2025.emnlp-main)

Copied to clipboard

Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang

Challenge:	Existing methods to identify the origin of AI-generated texts fail to identify origin due to the high similarity of different LLMs.
Approach:	They propose a black-box AI-generated text origin detection method which accurately predicts the origin of an input text by extracting distinct context inference patterns.
Outcome:	The proposed method outperforms 10 state-of-the-art baselines and achieves a 25% increase in AUC score on average across natural language and code datasets.