Leveraging Label Semantics and Entity Description Generation for LLM-based Fine-grained Entity Typing

ACL ARR 2026 January Submission9267 Authors

Keywords: Fine-grained Entity Typing, Large Language Models, Distant Supervision, Retrieval-based Candidate Selection, Descriptor Learning, Noisy Supervision

Abstract:

Fine-grained entity typing (FET) aims to assign semantically rich and contextually appropriate types to entity mentions.
While recent studies have explored the use of large language models (LLMs) for this task, two key challenges persist. First, FET typically involves a large number of entity types, making it difficult for LLMs to perform accurate classification. Second, the presence of label noise in the training data introduced by automatic supervision methods hinders effective fine-tuning.
To address these challenges, we propose DR-FET, a descriptor-based retrieval-augmented framework that reduces the effective label space and constructs high-precision training data under noisy supervision.
Our method introduces natural language descriptors as an intermediate semantic representation for both entity mentions and types.
During inference, entity descriptors are used to retrieve a small set of semantically relevant candidate types, enabling the LLM to perform fine-grained classification under explicit candidate constraints.
During training, the same descriptor and retrieval mechanism is reused to identify high-confidence instances from distantly supervised data, prioritizing label precision for efficient fine-tuning.
Experiments on two widely used benchmarks demonstrate that the proposed method consistently outperforms existing fine-grained entity typing approaches under noisy supervision.

Paper Type: Long

Research Area: Information Extraction and Retrieval

Research Area Keywords: named entity recognition and relation extraction, knowledge base construction, zero/few-shot extraction, entity linking/disambiguation, document-level extraction

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 9267