How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness

arXiv:2512.15634 · cs.CL, cs.AI, cs.LG · Submitted 2025-12-17 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2025-12-17

Updated: 2025-12-17

Terminology

• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 14 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 3 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 1× in this paper · explained in 5 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering