Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results
arXiv:2607.11183
The paper proposes Amplitude Gating, an inference‑time method that adjusts FFN activation magnitudes to improve tool‑structured outputs of large language models without changing model weights, and evaluates it across several Qwen models.
Abstract
Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plausible responses. We study inference-time feed-forward network (FFN) intervention as a way to improve structured outputs without retraining model weights. An earlier project-specific approach, Orthogonal Residual Projection (ORP), exposed sensitive SwiGLU FFN sites and non-monotonic energy effects, but its direction-changing operation produced more regressions than repairs in a key diagnostic. We therefore propose Amplitude Gating (AG), which preserves pretrained FFN weight directions and modulates activation magnitudes during decoding. AG separates candidate generation, ranking, and a prospective acceptance/fallback decision. We also introduce Per-Sample Fix-Harm Evaluation (PFHE), a paired reporting protocol that complements native task metrics with fixes, harms, preserved-correct cases, and preserved-wrong cases. On the only cross-position union that passes source-alignment audit, an exploratory offline mixed selector raises the descriptive heterogeneous-scorer Qwen3.5-9B tool-route micro-average from 38.66% to 42.92% (+4.27 percentage points); two Hermes function-call endpoints improve by +7.64 and +7.62 points. The same-output PFHE-format view records 48 fixes, 26 harms, 294 preserved-correct cases, and 2,188 preserved-wrong cases over 2,556 units, with positive paired bootstrap intervals for native and strict effects. Protocol-separated Qwen3-8B and Qwen2.5-7B analyses retain oracle headroom but no positive train-selected fixed tool route. A grouped five-fold RF diagnostic suggests weak nonlinear ranking signal but forces intervention, lacks baseline fallback and paired uncertainty, and is not deployment evidence. The results support model- and task-specific selection with strict fallback, not a universal AG switch.
30 pages, 9 figures