Get Started
Home
Topics
Search
Library
Research questionHow can NLP systems extract implicit, contextually inferred entities when labeled training data is scarce?Many texts imply entities through context instead of naming them directly, which conventional extraction methods often miss. Training systems to identify these latent entities is difficult when labeled examples are limited.
AI
Evaluation & Benchmarks
Information Retrieval
Machine Learning
Natural Language Processing
Retrieval-Augmented Generation
Small / On-device Models
Latest papersRecent research connected to this question, newest first.LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMsThe source addresses latent entity extraction with smaller instruction-tuned language models and synthetic data generation. It reports results across multiple tasks, including the MTEB Clustering Benchmark, and examines generalization to unseen domains relevant to retrieval-augmented generation, customer persona analysis, and knowledge graph enrichment.research paper · Sep 3, 2026
Related questions
How can NER systems decide when external retrieval helps long-tail entities without adding noise or cost?How can language models recognize unknown entities and refuse to invent relational facts?How should low-resource LLM fine-tuning use task-level language priors with ambiguous or incomplete data?How can we construct accurate knowledge bases from an LLM’s parametric knowledge without retrieval, fine-tuning, or exceeding 32B parameters?