---
license: apache-2.0
pipeline_tag: text-generation
tags:
  - lfm2
  - data-use
  - data-mentions
  - extraction
  - sft
  - lora
---

# lfm2.5-350M-datause-prwp

LoRA SFT of `LiquidAI/LFM2.5-350M` for data-mention extraction: emit the
data-bearing phrases in a text as compact JSON
(`data_mentions` with `data_mention`/`specificity_type`).

## Training
- base model: `LiquidAI/LFM2.5-350M`
- dataset: `rafmacalaba/data-use-mention-sft`
- epochs: 3
- learning rate: 0.0002
- LoRA: r=16 alpha=32 dropout=0.05
- completion-only masking (loss on assistant JSON turn)

## Evaluation (holdout, n=9079)

Jaccard entity-level matching: acronym-aware span clustering +
Hungarian optimal bipartite match (match thr=0.5), F0.5
primary. Aligned with `rafmacalaba/gliner_datause_extended`. The
holdout is `rafmacalaba/data-use-mention-sft`, so numbers are **not
directly comparable** to the GLiNER model's `data-use-mentions-extended`
holdout.

| label | tp | fp | fn | precision | recall | f0.5 | f1 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| **overall** | 9888 | 2537 | 2414 | 0.7958 | 0.8038 | 0.7974 | 0.7998 |
## Per-label

| label | tp | fp | fn | precision | recall | f0.5 | f1 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| descriptive | 4034 | 1930 | 1762 | 0.6764 | 0.6960 | 0.6802 | 0.6861 |
| named | 4183 | 1281 | 1175 | 0.7656 | 0.7807 | 0.7685 | 0.7731 |
| vague | 488 | 539 | 662 | 0.4752 | 0.4243 | 0.4641 | 0.4483 |
## Per-corpus

| label | tp | fp | fn | precision | recall | f0.5 | f1 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| prwp | 9888 | 2537 | 2414 | 0.7958 | 0.8038 | 0.7974 | 0.7998 |
## Per-origin

| label | tp | fp | fn | precision | recall | f0.5 | f1 |
| --- | --- | --- | --- | --- | --- | --- | --- |
| general_prwp | 9888 | 2537 | 2414 | 0.7958 | 0.8038 | 0.7974 | 0.7998 |

## Sample predictions (holdout)

| gold | predicted |
| --- | --- |
| {"data_mentions":[{"data_mention":"administrative data","specificity_type":"descriptive"}]} | {"data_mentions":[{"data_mention":"administrative data","specificity_type":"descriptive"}]} |
| {"data_mentions":[{"data_mention":"World Development Indicators","specificity_type":"named"},{"data_mention":"CPHS","spe | {"data_mentions":[{"data_mention":"World Development Indicators","specificity_type":"named"},{"data_mention":"CPHS","spe |
| {"data_mentions":[{"data_mention":"ES data","specificity_type":"named"}]} | {"data_mentions":[{"data_mention":"ES data","specificity_type":"named"}]} |
| {"data_mentions":[]} | {"data_mentions":[{"data_mention":"EUROMOD I4.0+","specificity_type":"named"}]} |
| {"data_mentions":[{"data_mention":"World Development Indicators","specificity_type":"named"},{"data_mention":"IMF World  | {"data_mentions":[{"data_mention":"World Development Indicators","specificity_type":"named"},{"data_mention":"IMF World  |
| {"data_mentions":[]} | {"data_mentions":[]} |
| {"data_mentions":[{"data_mention":"UNESCO-provided data","specificity_type":"descriptive"}]} | {"data_mentions":[{"data_mention":"PIRLS","specificity_type":"named"},{"data_mention":"UNESCO-provided data","specificit |
| {"data_mentions":[{"data_mention":"IHPS dataset","specificity_type":"named"},{"data_mention":"IHS4 data","specificity_ty | {"data_mentions":[{"data_mention":"IHS4 dataset","specificity_type":"named"},{"data_mention":"IHS4 data","specificity_ty |
| {"data_mentions":[{"data_mention":"HFSSS","specificity_type":"named"}]} | {"data_mentions":[{"data_mention":"HFSSS","specificity_type":"named"}]} |
| {"data_mentions":[{"data_mention":"HFCS data","specificity_type":"named"}]} | {"data_mentions":[{"data_mention":"HFCS data","specificity_type":"named"}]} |
| {"data_mentions":[{"data_mention":"data on patents and publications","specificity_type":"descriptive"}]} | {"data_mentions":[{"data_mention":"data on patents and publications","specificity_type":"descriptive"}]} |
| {"data_mentions":[{"data_mention":"UN COMTRADE Statistics","specificity_type":"named"}]} | {"data_mentions":[{"data_mention":"UN COMTRADE Statistics","specificity_type":"named"}]} |