5 papers
Chain Of Thought Compression: A Theoretical Analysis
Juncai Li, Ru Li, Yuxiang Zhou +2
Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive computational costs due to generati…
Consistency-Aware Editing for Entity-level Unlearning in Language Models
Xiaoqi Han, VÃctor Gutiérrez-Basulto, Ru Li +3
Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all kn…
Uncovering and Mitigating Transient Blindness in Multimodal Model Editing
Xiaoqi Han, Ru Li, Ran Yi +4
Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by rely…
HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation
Zhiwei Hu, VÃctor Gutiérrez-Basulto, Zhiliang Xiang +2
In a hyper-relational knowledge graph (HKG), each fact is composed of a main triple associated with attribute-value qualifiers, which express additional factual knowledge. The hype…
Multi-level Mixture of Experts for Multimodal Entity Linking
Zhiwei Hu, VÃctor Gutiérrez-Basulto, Zhiliang Xiang +2
Multimodal Entity Linking (MEL) aims to link ambiguous mentions within multimodal contexts to associated entities in a multimodal knowledge base. Existing approaches to MEL introdu…