Papers by Datao You
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing red-team methods rely on modifying user prompts, which lack adaptability to new data and may impact the agent’s performance. |
| Approach: | They propose a framework that implicitly manipulates the agent’s reasoning trajectory and memory retrieval with three key stages: Trigger Extraction, Reasoning Hijacking, and Constraint Tightening. |
| Outcome: | The proposed framework shows outstanding performance in cross-model and cross-scenario environments. |
Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak methods face an excessive number of iterative queries and poor generalization across models. |
| Approach: | They propose a jailbreak method that employs **I**ntent **C**oncealment and div**E**rsion to circumvent security constraints. |
| Outcome: | The proposed method outperforms existing jailbreak techniques in question-answering and text-generation tasks. |
Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods based on neural networks and pre-trained models consume substantial memory for training and text-graph construction. Existing models require access to the test dataset during the training phase, which means that when encountering new text data, the existing model needs to be retrained. |
| Approach: | They propose a low-resource and fast text classification model called LFTC to address these challenges by mining regularity information within intra-class data. |
| Outcome: | The proposed model improves performance and processing time under limited computational and data resources on 9 publicly available datasets. |