← Back to all news
arXiv AI By Jeesu Jung, Hwan Chang, Juseon Do, Jeonghwan Choi, Jinho Choo, Sungwoo Nam, S. K. Hong, Hwanjun Song

Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts

Read the original on arXiv AI →

Ready2Blend is a method that blends natural-language instructions with learned alignment prompts to enable continual alignment of large language models without retraining the backbone. It uses AlignFormer to map each requirement to a fixed-length prompt stored in a modular bank, while keeping the backbone and prior prompts frozen. The approach achieves 93.1–98.5% of joint‑training performance, retains prior knowledge, and reduces training time by up to 4.3×, also allowing weighted personalization and order‑free composition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 11

Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

arXiv:2603. 12658v2 Announce Type: replace-cross Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting, a critical limitation of the static pre-training paradigm inherent to modern LLMs.

By Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li, Xuemin Lin
llmsfine-tuningbenchmarkssafety
More like this →
arXiv AI
Sep 2

Prompt-Robust Language Models: Which Training Strategies Work?

The paper investigates how different training strategies affect the prompt sensitivity of large language models. It reproduces and compares methods such as refined data construction and robustness objectives, finding that while robustness fine‑tuning improves over standard fine‑tuning and in‑context learning, the prompt gap remains large (40–57%). Notably, newer techniques like CoIN and PPCL often underperform a simple data‑construction approach that uses one template per batch, and diagnostics suggest that mixed‑template batches force the optimizer to reconcile conflicting updates rather than learn a prompt‑agnostic representation.

By Frederic Sadrieh, Michal \v{S}tef\'anik
llmsfine-tuningsafety
More like this →
arXiv Machine Learning
Sep 10

RePro: Training Language Models to Faithfully Recycle the Web for Pretraining

RePro is a web‑recycling technique that trains a small language model (as little as 1 B parameters) with reinforcement learning to produce high‑quality, faithful rephrasings of pretraining data. The method uses one quality reward and three faithfulness rewards to preserve core semantics and structure while converting organic data into better training examples. Experiments show that RePro boosts downstream accuracy by 3.7–14.5 % over organic‑only baselines and improves data efficiency 2–3×, outperforming prior prompting‑based recycling approaches.

By Zichun Yu, Chenyan Xiong
llmsreinforcement-learningbenchmarks
More like this →