Tag
This paper introduces a framework for multilingual multimodal entity linking that improves accuracy on rare entities by combining reasoning and retrieval, with significant gains on the MERLIN benchmark.
The paper introduces Sci-ZSEL, a cost-efficient zero-shot scientific entity linking framework that selectively uses LLMs and an ontology-aware filter to enhance performance on benchmarks with low lexical overlap.
This paper presents GPTKB 2.0, a large-scale disambiguated knowledge base derived from LLMs, containing 38.4M triples over 1.6M canonical entities. It offers a web interface for browsing, SPARQL/ natural language querying, and auditing fact provenance and disambiguation decisions.
The article investigates whether recurring LLM workloads can be replaced by automatically synthesized deterministic pipelines of typed ML/NLP operators, and asks for feedback on feasibility and approaches.
This paper introduces ISEE, an interactive system that uses LLM-based agents to assess and collaboratively enrich the semantic quality of database field descriptions, reducing cognitive load and improving downstream tasks like entity linking.
Presents TELLER, a dual-path iterative preference optimization approach for table entity linking, with direct-answer and reasoning paths that improve accuracy on TableInstruct and MammoTab V2 benchmarks.
LELA is an LLM-based entity linking framework that combines zero-shot NER and entity disambiguation into an end-to-end Python library, validated across diverse settings.
BeLink introduces a set-wise instruction-tuning formulation for generative re-ranking in biomedical entity linking, achieving 3-24% accuracy improvements and faster inference compared to state-of-the-art systems.
This paper presents a corpus-centric diagnostic framework for analyzing biomedical NER and EL benchmarks, revealing substantial differences across nine corpora and arguing that standard statistics are insufficient for characterizing evaluation demands.