SCALPEL: Selective Capability Ablation via Low-rank Parameter Editing for Large Language Model Interpretability Analysis
Large language models excel across diverse domains, yet their deployment in healthcare, legal systems, and autonomous decision-making remains limited by incomplete understanding of their internal mechanisms. As these models integrate into high-stakes systems, understanding how they encode capabilities has become fundamental to interpretability research. Traditional approaches identify important modules through gradient attribution or activation analysis, assuming specific capabilities map to specific components. However, this oversimplifies neural computation: modules may contribute to multiple capabilities simultaneously, while single capabilities may distribute across multiple modules. These coarse-grained analyses fail to capture fine-grained, distributed capability encoding. We present SCALPEL (Selective Capability Ablation via Low-rank Parameter Editing for Large language models), a framework representing capabilities as low-rank parameter subspaces rather than discrete modules. Our key insight is that capabilities can be characterized by low-rank modifications distributed across layers and modules, enabling precise capability removal without affecting others. By training LoRA adapters to reduce distinguishing correct from incorrect answers while preserving general language modeling quality, SCALPEL identifies low-rank representations responsible for particular capabilities while remaining disentangled from others. Experiments across diverse capability and linguistic tasks from BLiMP demonstrate that SCALPEL successfully removes target capabilities while preserving general capabilities, providing fine-grained insights into capability distribution across parameter space. Results reveal that capabilities exhibit low-rank structure and can be selectively ablated through targeted parameter-space interventions, offering nuanced understanding of capability encoding in LLMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation
Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited i…
Action SegmentationSCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning
We propose SCALPEL, a flexible method for object segmentation that integrates rich region-merging cues with midand high-level information about object layout, class, and scale into the segmentation process. Unlike compet…
ObjectRe-RankingSegmentationSemantic SegmentationPrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing …
MemorizationPrivacy PreservingScalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
Rapid progress in large vision-language models (LVLMs) has achieved unprecedented performance in vision-language tasks. However, due to the strong prior of large language models (LLMs) and misaligned attention across mod…
High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to…
parameter-efficient fine-tuning