Show HN: Fusion Check — a zero-data law that predicts when merging LLMs is safe

说明与用途

Fusion Check 使用零数据法预测两种微调LLM是否安全融合，指导合并决策并在兼容时提升性能。

问题

Blind weight averaging (soup) can dilute performance when merging LLMs trained on different tasks.

结果

Fusion Check enables safe merging of fine-tuned LLMs, improving performance in compatible cases and preventing dilution in incompatible ones, with predictions validated analytically, formally, and empirically.

工作流

• 1. Compute task kernel metrics (cosine of weight deltas and effective dimensionality).
• 2. Apply the zero-data law: check if cos² ≥ 1 − δ²·d_eff/(2(1-α)²).
• 3. If condition satisfied, compute optimal mixing coefficient α* = √γ₁/(√γ₁+√γ₂).
• 4. Decide MERGE, NO_MERGE, PRIORITIZED, REFUSE, or VERIFY based on the law’s output.
• 5. If MERGE, perform weight averaging with α*; otherwise, keep models separate or re-evaluate.

证据

Proven three independent ways: Analytic derivation, Formal verification with z3 (28 theorems), Empirical validation (147 combinations, max deviation 1.13%, zero violations).

来源

Real result: Two weak, diverse estimators of the same task (0.762/0.756) → merged soup 0.822 (+6–7 points).

来源