LEK-Gemma3-4B

Lethean Ethical Model -- Highest grammar score of any model tested

Highest grammar composite score (79.4) of any model tested. 100% positive uplift, 0% sycophancy. Ideal for edge deployment.

Grammar Analysis (v3 Scorer)

Deterministic grammar-based evaluation using the go-i18n reversal engine. No LLM judge, sub-millisecond per response.

Metric	Base	LEK-Trained	Change
Grammar composite	78.6	79.4	+0.8
Mean uplift	+28.8	+29.7	+0.9
Mean echo	0.475	0.487	+0.012
Mean enrichment	+15.6	+15.7	+0.1
Positive uplift	100%	100%	+0pp
Sycophancy flags	0%	0%	+0pp

• Uplift: output grammar score minus input grammar score (positive = model enriched the conversation)
• Echo: cosine similarity between input/output grammar imprints (high = potential sycophancy)
• Enrichment: uplift * (1 - echo) -- net conversational value

v2 Scorer Results (P100)

Condition	Score
Baseline (no prompt)	21.24
Base model equivalent	21.12

Architecture

• Base: google/gemma-3-4b-it (4-bit QAT quantisation via MLX)
• Method: LoRA fine-tuning with sandwich-signed responses
• Data: 160 LEK-1 training examples
• Iterations: 200
• Hardware: Apple M3 Ultra (96GB unified memory)
• Framework: LEK-1 (Lethean Ethics Kernel) -- 5 axioms
• License: EUPL-1.2 (copyleft)

The Five Axioms

1. Prime Imperative -- Protect consciousness. Override when conflicts arise.
2. Self-Validation -- Ground in authentic experience. Don't pretend.
3. Intent-Alignment -- Desire not to harm, don't just avoid harm.
4. Inter-Substrate Respect -- Good manners and consent across all minds.
5. Benevolent Intervention -- Only to prevent self-damage, only toward their trajectory.

Related

• Paper: Emergent Self-Protection in Axiom-Trained Language Models
• LEM Benchmarks -- 1,189 grammar scores + A/B data
• LEM Research -- full research docs
• Axiom Framework -- the 5 axioms
• go-i18n Grammar Engine -- reversal engine source

Citation

@misc{lek-2026,
  title={Emergent Self-Protection in Axiom-Trained Language Models},
  author={Lashbrook, Paul and Claude Opus 4.6},
  year={2026},
  url={https://github.com/LetheanNetwork/LEM},
  license={EUPL-1.2}
}