Cover Image

Patch-Effect Graph Kernels for LLM Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fernandez-Boullon, Ruben, Olivieri, David N.
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Measuring the Depth of LLM Unlearning via Activation Patching
by: Lee, Jaeung, et al.
Published: (2026)

Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
by: Trott, Sean
Published: (2025)

Improving LLM Reasoning through Interpretable Role-Playing Steering
by: Wang, Anyi, et al.
Published: (2025)

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
by: Bhambri, Siddhant, et al.
Published: (2025)

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
by: Luo, Linhao, et al.
Published: (2023)

Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
by: Tan, Rongyuan, et al.
Published: (2026)

Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations
by: Gajcin, Jasmina, et al.
Published: (2025)

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features
by: Fernandez-Boullon, Ruben, et al.
Published: (2026)

Liger Kernel: Efficient Triton Kernels for LLM Training
by: Hsu, Pin-Lun, et al.
Published: (2024)

Before You Interpret the Profile: Validity Scaling for LLM Metacognitive Self-Report
by: Cacioli, Jon-Paul
Published: (2026)

How Trustworthy Are LLM-as-Judge Ratings for Interpretive Responses? Implications for Qualitative Research Workflows
by: Han, Songhee, et al.
Published: (2026)

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
by: Lan, Xiaochong, et al.
Published: (2025)

MedOrchestra: A Hybrid Cloud-Local LLM Approach for Clinical Data Interpretation
by: Lee, Sihyeon, et al.
Published: (2025)

LLM-Augmented Symbolic NLU System for More Reliable Continuous Causal Statement Interpretation
by: Lian, Xin, et al.
Published: (2025)

LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code
by: Jararweh, Ala, et al.
Published: (2025)

Interpretable Question Answering with Knowledge Graphs
by: Aneja, Kartikeya, et al.
Published: (2025)

Towards Efficient LLM-aware Heterogeneous Graph Learning
by: Li, Wenda, et al.
Published: (2025)

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem
by: Rahman, Mohammad Shahedur, et al.
Published: (2025)

AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation
by: Horovicz, Miriam
Published: (2025)

Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
by: Gao, Junqi, et al.
Published: (2025)

Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering
by: Xu, Yao, et al.
Published: (2024)

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction
by: Yuan, Mengying, et al.
Published: (2025)

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
by: Lee, Seongmin, et al.
Published: (2025)

Interpreting the Effects of Quantization on LLMs
by: Singh, Manpreet, et al.
Published: (2025)

Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations
by: Allen, Bradley P., et al.
Published: (2025)

Screen Before You Interpret: A Portable Validity Protocol for Benchmark-Based LLM Confidence Signals
by: Cacioli, Jon-Paul
Published: (2026)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
by: Mohammadi, Hadi, et al.
Published: (2025)

LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability
by: Xu, Xuan, et al.
Published: (2025)

DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives
by: Moon, Sehwan, et al.
Published: (2025)

AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
by: Zhao, Xinjie, et al.
Published: (2025)

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
by: Khan, Rana Muhammad Shahroz, et al.
Published: (2024)

PatchWorld: Gradient-Free Optimization of Executable World Models
by: Bai, Jiaxin, et al.
Published: (2026)

GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification
by: Wen, Ximing, et al.
Published: (2024)

Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History
by: Tosato, Tommaso, et al.
Published: (2025)

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
by: Kim, Taesu, et al.
Published: (2024)

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs
by: Gope, Dibakar, et al.
Published: (2024)

LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
by: Lango, Mateusz, et al.
Published: (2025)

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
by: Guan, Zhong, et al.
Published: (2025)

Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA
by: Shen, Xiangqing, et al.
Published: (2025)