PIVOINE: Instruction Tuning for Open-world Entity Profiling
Keming Lu, Xiaoman Pan, Kaiqiang Song, Hongming Zhang, Dong Yu, Jianshu Chen · 2023
This work considers the problem of Openworld Entity Profiling, which is a sub-domain of Open-world Information Extraction (Openworld IE).Unlike the conventional closedworld IE, Open-world IE considers a more general situation where entities and relations could be beyond a predefined ontology.We seek to develop a large language model (LLM) that can perform Open-world Entity Profiling with instruction tuning to extract desirable entity profiles characterized by (possibly fine-grained) natural language instructions.In particular, we construct INSTRUCTOPEN-WIKI, a substantial instruction-tuning dataset for Open-world Entity Profiling enriched with a comprehensive corpus, extensive annotations, and diverse instructions.We finetune pretrained BLOOM models on INSTRUCTOPEN-WIKI and obtain PIVOINE, an LLM for Openworld Entity Profiling with strong instructionfollowing capabilities.Our experiments demonstrate that PIVOINE significantly outperforms traditional methods and ChatGPT-based baselines, displaying impressive generalization capabilities on both unseen instructions and outof-ontology cases.Consequently, PIVOINE emerges as a promising solution to tackle the open-world challenge in entity profiling.1