From LoRA to Language: Recovering Skill Documents from Adapters
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- LoRA: Low-Rank Adaptation of Large Language Models
- Text-to-LoRA: Instant Transformer Adaption
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
- LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
- Parametric Skills
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters
- W2T: LoRA Weights Already Know What They Can Do
- Learning to Interpret Weight Differences in Language Models
- Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
- Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- Parameter-Efficient Transfer Learning for NLP
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
- LoRA Learns Less and Forgets Less
- HyperNetworks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis