Cover Image

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Lin, Hu, Lijie, Wang, Di
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
by: Wang, Xinhai, et al.
Published: (2025)

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
by: Jiang, Xinyan, et al.
Published: (2026)

Controlling Repetition in Protein Language Models
by: Zhang, Jiahao, et al.
Published: (2026)

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
by: Zhang, Lin, et al.
Published: (2025)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
by: Jiang, Xinyan, et al.
Published: (2025)

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
by: Zhang, Zhuoran, et al.
Published: (2025)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
by: Kim, Geonhee, et al.
Published: (2024)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
by: Mao, Yingzhi, et al.
Published: (2025)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
by: Che, Liwei, et al.
Published: (2026)

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
by: Żukowska, Nina, et al.
Published: (2026)

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
by: Yang, Qishun, et al.
Published: (2026)

Understanding the Dynamics of Demonstration Conflict in In-Context Learning
by: Jiao, Difan, et al.
Published: (2026)

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
by: Zhu, Rongzhi, et al.
Published: (2025)

In-Run Data Shapley for Adam Optimizer
by: Ding, Meng, et al.
Published: (2026)

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
by: Li, Hongji, et al.
Published: (2025)

Unveiling the Reasoning Process of Large Language Models
by: Zhang, Junjie, et al.
Published: (2026)

Evaluating Data Influence in Meta Learning
by: Ren, Chenyang, et al.
Published: (2025)

Predicting LLM Output Length via Entropy-Guided Representations
by: Xie, Huanyi, et al.
Published: (2026)

The Compositional Architecture of Regret in Large Language Models
by: Cui, Xiangxiang, et al.
Published: (2025)

From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
by: Zhang, Jue, et al.
Published: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
by: Jiang, Xinyan, et al.
Published: (2026)

Certified Circuits: Stability Guarantees for Mechanistic Circuits
by: Anani, Alaa, et al.
Published: (2026)

Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
by: Ren, Zirui, et al.
Published: (2026)

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
by: Li, Tianle, et al.
Published: (2025)

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
by: Wang, Shaobo, et al.
Published: (2025)

AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
by: Bao, Zhixuan, et al.
Published: (2026)

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
by: Sun, Zhongxiang, et al.
Published: (2025)

Improving Interpretation Faithfulness for Vision Transformers
by: Hu, Lijie, et al.
Published: (2023)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
by: Dai, Xinnan, et al.
Published: (2025)

Private Language Models via Truncated Laplacian Mechanism
by: Huang, Tianhao, et al.
Published: (2024)

Faithful Interpretation for Graph Neural Networks
by: Hu, Lijie, et al.
Published: (2024)

Toward Mechanistic Explanation of Deductive Reasoning in Language Models
by: Maltoni, Davide, et al.
Published: (2025)

A Mechanistic Analysis of Looped Reasoning Language Models
by: Blayney, Hugh, et al.
Published: (2026)

Dissecting Representation Misalignment in Contrastive Learning via Influence Function
by: Hu, Lijie, et al.
Published: (2024)

Editable Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
by: Ildiz, M. Emrullah, et al.
Published: (2024)

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
by: He, Jesse, et al.
Published: (2026)

Skill Path: Unveiling Language Skills from Circuit Graphs
by: Chen, Hang, et al.
Published: (2024)

PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
by: Yu, Manjiang, et al.
Published: (2025)

Self-supervised Hierarchical Visual Reasoning with World Model
by: Xu, Yuanfei, et al.
Published: (2026)