PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
arXiv preprint arXiv:2501.06252 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CL 3years
2026 3roles
background 2polarities
background 2representative citing papers
SCoL trains LLMs via meta-reinforcement learning to generate layer-specific update instructions that improve knowledge acquisition and retention from context streams over standard baselines.
On a widened 1536-dimensional substrate, a router rewrite explains the full +0.0426 nat log-PPL gain of an evolutionary MoLoRA system while the lifecycle component imposes a -0.028 nat drag and the headline full-system gain fails to reach significance at n=3 seeds.
citing papers explorer
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
-
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
SCoL trains LLMs via meta-reinforcement learning to generate layer-specific update instructions that improve knowledge acquisition and retention from context streams over standard baselines.
-
Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary
On a widened 1536-dimensional substrate, a router rewrite explains the full +0.0426 nat log-PPL gain of an evolutionary MoLoRA system while the lifecycle component imposes a -0.028 nat drag and the headline full-system gain fails to reach significance at n=3 seeds.