---
license: mit
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- peft
- conditional-prefix-memory-tuning
- cefr-alignment
- topic-aligned
- balanced-subset
---
# Balanced Topic-Aligned C-PMT Global Controller

This experiment evaluates the impact of incorporating explicit `topic_title` prompt metadata during C-PMT training on a balanced subset of EFCAMDAT (~5.5K total samples).

## Experimental Setup
1. **Topic Alignment:** Prompt contexts incorporate `topic_title` directly, allowing the frozen base model to handle semantic content while the C-PMT controller isolates structural CEFR steering.
2. **Blind Level Control:** The text prompt contains no target CEFR text instructions. Control is enforced exclusively via the continuous `cefr_id` architectural knob.
3. **Loss:** Standard cross-entropy causal language modeling loss on balanced target tokens.