Knowledgator Engineering has released GLiFormer, a schema-conditioned encoder framework for information extraction. A single model handles named-entity recognition (NER), text classification, relation extraction, nested JSON structuring, and text embeddings. Labels and extraction schemas are supplied at inference time. Two checkpoints are available on Hugging Face: GLiFormer Base v1 with 264.2M parameters and GLiFormer Large v1 with 575.6M parameters.
Deployable today? Yes. Both checkpoints are released under the Apache 2.0 license, install with pip install gliformer, and run on CPU or GPU โ a practical advantage as enterprises in 2026 increasingly demand efficient, self-hostable extraction pipelines that avoid per-token LLM inference costs.
The Problem It Targets
Extraction stacks often chain separate models: one tags entities, another classifies documents, and a third rebuilds records. The research team argues these tasks share one core operation โ encode the source, represent the requested concepts, then score their compatibility.
Large language models can emit nested JSON, but they generate field names, punctuation, and values token by token. GLiFormer removes output generation from that path entirely.
How GLiFormer Works
GLiFormer builds on GLiNER and generalizes its label matching through an "anchor." An anchor is the object each runtime label gets scored against. It can be a group vector for classification, an entity pair for relations, or a record slot.
The source is encoded once. Multiple schemas for the same document then run as task-local groups over that shared encoding. Head compute still grows with the number of groups, labels, and anchors.
For NER, the head scores start, end, and inside evidence for every token and label pair. Independent sigmoid outputs let nested mentions and shared boundaries coexist.
Structuring runs in four stages:
- Ground field values as spans taken directly from the source text.
- Assign spans to unordered record slots, trained with Hungarian matching.
- Predict directed parent-child links, restricted to paths the schema allows.
- Assemble nested JSON with a deterministic decoder.
via MarkTechPost