Domain Restriction via Multi SAE Layer Transitions

• URL: http://arxiv.org/abs/2605.11920v1
• Date: Tue, 12 May 2026 10:36:02 GMT
• Title: Domain Restriction via Multi SAE Layer Transitions
• Abstract summary: We show that layer transitions provide a promising avenue for extracting domain-specific signature.<n>Specifically, we present several lightweight ways of learning on internal dynamics encoded using a sparse autoencoder.<n>We provide a comprehensive analysis of the method and benchmark it with the gemma-2 2B and 9B models.
• Score: 0.20052993723676893
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The general-purpose nature of Large Language Models (LLMs) presents a significant challenge for domain-specific applications, often leading to out-of-domain (OOD) interactions that undermine the provider's intent. Existing methods for detecting such scenarios treat the LLM as an uninterpretable black box and overlook the internal processing of inputs. In this work we show that layer transitions provide a promising avenue for extracting domain-specific signature. Specifically, we present several lightweight ways of learning on internal dynamics encoded using a sparse autoencoder (SAE) that exhibit great capability in distinguishing OOD texts. Building on top of SAEs representation transitions enables us to better interpret the LLM internal evolution of input processing and shed light on its decisions. We provide a comprehensive analysis of the method and benchmark it with the gemma-2 2B and 9B models. Our results emphasize the efficacy of the internal process in capturing fine-grained input-related details.

Related papers

• Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders [54.06522068041745]
  Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing.<n>While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this accuracy.<n>In this work, we investigate this performance gap, hypothesizing that it stems from treating the VLM as a condition encoder.
  arXiv  Detail & Related papers  (2026-07-07T16:11:13Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning [62.11389260206383]
  textscFineRS is a two-stage MLLM-based reinforcement learning framework for segmenting extremely small objects.<n>We present textscFineRS-4k, a new dataset for evaluating MLLMs on attribute-level reasoning and pixel-level segmentation on subtle, small-scale targets.
  arXiv  Detail & Related papers  (2025-10-24T10:14:17Z)
• Integrating Domain Knowledge into Process Discovery Using Large Language Models [3.7448613209842967]
  We propose an interactive framework that incorporates domain knowledge, expressed in natural language, into the process discovery pipeline.<n>The framework coordinates interactions among the Large Language Models (LLMs), domain experts, and a set of backend services.<n>Our empirical study includes a case study based on a real-life event log with the involvement of domain experts, who assessed the usability and effectiveness of the framework.
  arXiv  Detail & Related papers  (2025-10-08T15:59:11Z)
• Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains [6.323778761045108]
  Agentic large language models (LLMs) have become prominent for autonomously interacting with external environments.<n>This paper explores agent fine-tuning for domain adaptation within Hitachi's JP1 microdomain for specialized IT operations.
  arXiv  Detail & Related papers  (2025-10-01T04:04:53Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Teach Old SAEs New Domain Tricks with Boosting [3.3865605512957453]
  This paper introduces a residual learning approach that addresses this feature blindness without requiring complete retraining.<n>We propose training a secondary SAE specifically to model the reconstruction error of a pretrained SAE on domain-specific texts.<n>By summing the outputs of both models during inference, we demonstrate significant improvements in both LLM cross-entropy and explained variance metrics.
  arXiv  Detail & Related papers  (2025-07-17T10:57:49Z)
• Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs [56.76586846269894]
  Multimodal Large Language Models (MLLMs) have achieved success across various domains.<n>Despite its importance, the study of knowledge sharing among domain-specific MLLMs remains largely underexplored.<n>We propose a unified parameter integration framework that enables modular composition of expert capabilities.
  arXiv  Detail & Related papers  (2025-06-30T15:07:41Z)
• InverseScope: Scalable Activation Inversion for Interpreting Large Language Models [5.670123459649656]
  InverseScope is an assumption-light and scalable framework for interpreting neural activations via input inversion.<n>To address the inefficiency of sampling in high-dimensional spaces, we propose a novel conditional generation architecture.<n>We also introduce a quantitative evaluation protocol that tests interpretability hypotheses using the feature consistency rate computed over the sampled inputs.
  arXiv  Detail & Related papers  (2025-06-09T03:59:28Z)
• BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition [12.57768435856206]
  We propose an approach called Boundary-Aware LLMs for Few-Shot Named Entity Recognition.<n>We introduce a boundary-aware contrastive learning strategy to enhance the LLM's ability to perceive entity boundaries for generalized entity spans.<n>We utilize LoRAHub to align information from the target domain to the source domain, thereby enhancing adaptive cross-domain classification capabilities.
  arXiv  Detail & Related papers  (2024-12-03T07:51:14Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.