3 citations · 3 across the 3 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts
Jeesu Jung, Hwan Chang, Juseon Do +5
Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are flexible and composable but offer…
cs.AI2026
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim, Namgyu Ho, Sangmin Hwang +7
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt th…