Model Releases
Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts
arXiv:2609.39365v1 Announce Type: cross Abstract: Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are fle
arXiv:2609.39365v1 Announce Type: cross Abstract: Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are flexible and composable but offer only indirect control, whereas post-training provides stronger adaptation at the cost of repeated parameter updates. We introduce Ready2Blend, which combines the flexibility of natural language with learned alignment. AlignFormer maps each requirement to a fixed-length alignment prompt stored in a modular prompt bank, while the backbone and prior prompts remain frozen. Composability regularization transfers the semantic geometry of textual requirements into prompt space, enabling inference-time blending and reweighting. Across two practical continual alignment settings, Ready2Blend is the only frozen-backbone method that matches post-training-based alignment methods, reaching 93.1-98.5% of a joint-training reference with competitive retention, while requiring only a few prompt tokens and up to 4.3imes less training time. Its modular design further enables weighted personalization and order-free composition without retraining. Code will be released upon acceptance.
Related
- Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages
- TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
- GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
Source: arXiv cs.AI | 2026-10-01