qwen3-coder-30b-a3b-ies4 (v1.3)

A LoRA fine-tune of Qwen3-Coder-30B-A3B that generates IES4 (UK Government Information Exchange Standard) RDF/Turtle from natural language. v1.3 adds targeted coverage of the IES construct families (measurement, assessment/PossibleWorld, facility+naming, vehicle/journey, meeting, kinship, rich communication) and is designed to run with a term-suggesting validator in the loop (neuro-symbolic).

Headline: how to actually use this (the loop matters)

A single forward pass drafts structurally-correct IES4 but, on scenarios far from the training distribution, reverts to plausible-but-wrong term spellings (ies:hasParticipant for ies:isParticipantIn, ies:MeasureUnit for ies:measureUnit). A term-suggesting validator closes this. Measured on held-out, out-of-distribution scenarios (real dstl sample-data idioms the model never trained on), IES4 term-conformance:

pipeline	OOD term-conformance
single forward pass	27%
+ repair loop ("term X is invalid")	45%
+ suggesting loop ("-> use ies:measureUnit")	82%

The suggesting validator (term_suggest.py, shipped in this repo) returns the nearest real IES4 term for any invalid one; the model applies the correction. This is the recommended production pipeline.

In-distribution eval (vs untuned base)

metric	base	v1.3
IES term conformance	0.0%	97.7%
hallucinated-term rate	0.942	0.005
structural conformance	0.911	0.977
multi-standard relation conf	91.7%	100.0%

Files

• fused 8-bit MLX weights (v1.3) - default when you mlx_lm generate --model this repo
• adapters_v13/ - the raw LoRA adapter (apply to the bf16 base with other toolchains)
• term_suggest.py - the term-suggesting validator (lexical + morphological + definition-overlap)
• repair_suggest_ood.py - the reference neuro-symbolic loop that scores 82% above

The finding (why this model is shaped this way)

A controlled study (v1.0->v1.3) showed OOD conformance is invariant to data volume (2k->22k examples) and linguistic diversity (9%->38% paraphrase), and that construct coverage fixes structure but not term-exactness. The binding constraint is term-exactness on novel compositions; the fix is a symbolic term-suggesting validator in the loop. This model is the "draft" half; term_suggest.py is the "perfect" half.

Limitations

• Without the loop, expect ~27% OOD term-conformance; run the loop.
• Two OOD residual classes remain even with the loop: concepts with no clean IES equivalent (a boat is modelled as a generic vehicle), and suggester-ranking misses (NamingScheme). Both are refinement targets, not walls.

Licensing

IES4: MIT, (C) Crown copyright Dstl. Multi-standard slice: Text2KGBench (CC-BY-SA-4.0, Mihindukulasooriya et al, ISWC 2023). Weights: MIT. By The Tesseract Academy.