Goodfire proposes adversarial parameter decomposition to break LLMs into faithful subcomponents
Sauers_ · x · 2026-10-02
Goodfire, with MATS and independent researchers, published "Interpreting Language Model Parameters," introducing adVersarial Parameter Decomposition (VPD) — a method that decomposes a language model's parameters into subcomponents, each implementing a small part of the learned algorithm.
- Core idea: only a small fraction of subcomponents is needed to account for the network's behavior on any input.
- Adversarial ablation: decompositions are optimized to preserve input-output behavior even under adversarially selected ablations, yielding short, mechanistically faithful descriptions of the network's algorithm.
- Why it matters: prior interpretability work focused on intermediate representations; this targets how parameters and nonlinearities actually compute on them.
More from Research
- Researcher calls METR/Anthropic '2x speedup' RSI analysis statistically dubious — jessi_cata · 2026-11-19
- Conviction invests in Xlue: health world model beats frontier models in blind disease prediction — XiongChenyan · 2026-11-19
- New Multi Agent Coordination Bench shows agent teams coordinate poorly, win by luck — billyuchenlin · 2026-11-19
- KradleBench pits humans and AI in live multi-agent Minecraft evals — lmoroney · 2026-11-19
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- OpenVax codebase grows from 78K to 565K lines in 15 months — iskander · 2026-11-19