RECAP benchmark finds that six prompt optimization methods show no significant performance gains under proactive continual adaptation to evolving constraints across four LLMs.
I ns CL : A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
PROXYMIX learns a dynamic replay controller on a small proxy model and transfers it to a large target model, improving accuracy by 3.4 points and reducing forgetting by 3.5 points on LLaMA-3-8B continual tuning sequences.
SynLearner lets LLMs improve synthetic data generation on later tasks in a stream by learning reusable patterns and balancing quality with diversity from feedback on earlier tasks.
citing papers explorer
-
RECAP: Regression Evaluation for Continual Adaptation of Prompts
RECAP benchmark finds that six prompt optimization methods show no significant performance gains under proactive continual adaptation to evolving constraints across four LLMs.
-
Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning
PROXYMIX learns a dynamic replay controller on a small proxy model and transfers it to a large target model, improving accuracy by 3.4 points and reducing forgetting by 3.5 points on LLaMA-3-8B continual tuning sequences.
-
Make LLM Learn to Synthesize from Streaming Experiences through Feedback
SynLearner lets LLMs improve synthetic data generation on later tasks in a stream by learning reusable patterns and balancing quality with diversity from feedback on earlier tasks.