← 研踪 PaperTrailarXiv:2602.02060 · v3
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
首次提交 2026-02-02 21:00
版本更新 2026-11-10 12:14
雷达观测 2026-11-11 13:08
摘要
Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly modulating reliance on different internal feature pathways. Existing approaches to shortcut and spurious behavior primarily rely on post hoc analysis or data-level interventions, offering limited ability to directly intervene on how models use information. We introduce FiLoRA (Focus-and-Ignore LoRA), an instruction-conditioned, parameter-efficient adaptation framework that enables controllable modulation of feature reliance while keeping the task and predictive objective fixed. FiLoRA decomposes adaptation into feature-aligned low-rank modules and applies instruction-conditioned gating, allowing natural language instructions to act as computation-level control signals over internal representations. We evaluate FiLoRA across both controlled classification settings and generative multimodal tasks, and under a range of instruction types, including natural and compositional instructions. Results show that FiLoRA induces consistent and interpretable shifts in feature reliance, selectively amplifying or suppressing different feature groups in accordance with the instruction, without altering task semantics. Our findings suggest that instruction-conditioned parameter adaptation can serve as a practical mechanism for intervening on internal model behavior, providing a new perspective on controllability and analysis of multimodal systems beyond output-level prompting or post hoc interpretation.
期刊信息：NeurIPS 2026
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-10 12:14 · 最新观测版本
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly modulating reliance on different internal feature pathways. Existing approaches to shortcut and spurious behavior primarily rely on post hoc analysis or data-level interventions, offering limited ability to directly intervene on how models use information. We introduce FiLoRA (Focus-and-Ignore LoRA), an instruction-conditioned, parameter-efficient adaptation framework that enables controllable modulation of feature reliance while keeping the task and predictive objective fixed. FiLoRA decomposes adaptation into feature-aligned low-rank modules and applies instruction-conditioned gating, allowing natural language instructions to act as computation-level control signals over internal representations. We evaluate FiLoRA across both controlled classification settings and generative multimodal tasks, and under a range of instruction types, including natural and compositional instructions. Results show that FiLoRA induces consistent and interpretable shifts in feature reliance, selectively amplifying or suppressing different feature groups in accordance with the instruction, without altering task semantics. Our findings suggest that instruction-conditioned parameter adaptation can serve as a practical mechanism for intervening on internal model behavior, providing a new perspective on controllability and analysis of multimodal systems beyond output-level prompting or post hoc interpretation.
查看此版本解读 →查看此版本原文 ↗