15 papers
Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents
Xi Wang, Songlei Jian, Yiming Zhang +5
As large language models increasingly operate as tool-using agents, post-jailbreak safety feedback is often assumed to serve as a reliable safeguard; however, how lingering jailbre…
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
Xi Wang, Songlei Jian, Shasha Li +5
Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specif…
Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization
Jinying Xiao, Bin Ji, Shasha Li +8
Large Language Models (LLMs) quantization facilitates deploying LLMs in resource-limited settings, but existing methods that combine incompatible gradient optimization and quantiza…
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
Xi Wang, Songlei Jian, Shasha Li +9
Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligne…
EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
Xiaopeng Li, Shasha Li, Xi Wang +7
Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted paramete…
Rethinking Residual Distribution in Locate-then-Edit Model Editing
Xiaopeng Li, Shanwen Wang, Shasha Li +4
Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a pr…
Model Editing for LLMs4Code: How Far are We?
Xiaopeng Li, Shangwen Wang, Shasha Li +6
Large Language Models for Code (LLMs4Code) have been found to exhibit outstanding performance in the software engineering domain, especially the remarkable performance in coding ta…
LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment
Binrui Zeng, Bin Ji, Xiaodong Liu +7
As Large Language Models (LLMs) demonstrate exceptional performance across various domains, deploying LLMs on edge devices has emerged as a new trend. Quantization techniques, whic…
Identifying Knowledge Editing Types in Large Language Models
Xiaopeng Li, Shasha Li, Shangwen Wang +5
Knowledge editing has emerged as an efficient technique for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there…
EMP: Enhance Memory in Data Pruning
Jinying Xiao, Ping Li, Jie Nie +6
Recently, large language and vision models have shown strong performance, but due to high pre-training and fine-tuning costs, research has shifted towards faster training via datas…
DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking
Shezheng Song, Shasha Li, Shan Zhao +7
Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base…
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
Xiaopeng Li, Shasha Li, Shezheng Song +8
The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources…
Span-based joint entity and relation extraction augmented with sequence tagging mechanism
Bin Ji, Shasha Li, Hao Xu +4
Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. However, since previous span-based models rely on…
SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder
Wuhang Lin, Shasha Li, Chen Zhang +4
Text summarization models are often trained to produce summaries that meet human quality requirements. However, the existing evaluation metrics for summary text are only rough prox…
Topic-Grained Text Representation-based Model for Document Retrieval
Mengxue Du, Shasha Li, Jie Yu +5
Document retrieval enables users to find their required documents accurately and quickly. To satisfy the requirement of retrieval efficiency, prevalent deep neural methods adopt a…