Llama318binstruct
1 mentions across 0 people
All mentions
Unknown speaker
Mixedpaper · 2026-06-11
“On the more heavily RLHF-tuned Llama-3.1-8B-Instruct the asymmetry strengthens, not heals: parametric memory's behavioral advantage collapses while its absence-calibration deficit against retrieval widens -- an alignment tax on parametric user-memory.”
Decomposing LLM User-Side Memory: Behavioral vs. Factual Components and Substrat ↗