URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
Linking a claim to grounded references is a critical ability to fulfill human demands for authentic and reliable information. Current studies are limited to specific tasks like information retrieval or semantic matching, where the claim-reference relationships are unique and fixed, while the referential knowledge linking (RKL) in real-world can be much more diverse and complex. In this paper, we propose universal referential knowledge linking (URL), which aims to resolve diversified referential knowledge linking tasks by one unified model. To this end, we propose a LLM-driven task-instructed representation compression, as well as a multi-view learning approach, in order to effectively adapt the instruction following and semantic understanding abilities of LLMs to referential knowledge linking. Furthermore, we also construct a new benchmark to evaluate ability of models on referential knowledge linking tasks across different scenarios. Experiments demonstrate that universal RKL is challenging for existing approaches, while the proposed framework can effectively resolve the task across various scenarios, and therefore outperforms previous approaches by a large margin.
Code (1)
Tasks
Information RetrievalInstruction FollowingMULTI-VIEW LEARNINGRetrievalSimilar Papers 제목 키워드 기반
Instructed Language Models with Retrievers Are Powerful Entity Linkers
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer fro…
Entity LinkingIn-Context LearningLook and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views
We introduce Look and Tell, a multimodal dataset for studying referential communication across egocentric and exocentric perspectives. Using Meta Project Aria smart glasses and stationary cameras, we recorded synchronize…
InstructEdit: Instruction-based Knowledge Editing for Large Language Models
Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited …
knowledge editingDRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking
Multimodal Entity Linking (MEL) is a task that aims to link ambiguous mentions within multimodal contexts to referential entities in a multimodal knowledge base. Recent methods for MEL adopt a common framework: they firs…
Entity LinkingRelationKnowledge-Rich Self-Supervision for Biomedical Entity Linking
Entity linking faces significant challenges such as prolific variations and prevalent ambiguities, especially in high-value domains with myriad entities. Standard classification approaches suffer from the annotation bott…
Contrastive LearningEntity Linking