Cover Image

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Haoming, Yan, Yibo, Huo, Jiahao, Zou, Xin, Li, Xinfeng, Wang, Kun, Hu, Xuming
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
by: Huang, Kaichen, et al.
Published: (2024)

MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model
by: Huo, Jiahao, et al.
Published: (2024)

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
by: Huo, Jiahao, et al.
Published: (2025)

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models
by: Zhang, Yuji, et al.
Published: (2024)

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
by: Yan, Yibo, et al.
Published: (2025)

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
by: Yan, Yibo, et al.
Published: (2026)

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
by: Zhang, Yuji, et al.
Published: (2025)

Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
by: Yan, Yibo, et al.
Published: (2026)

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
by: Yan, Yibo, et al.
Published: (2026)

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
by: Zhou, Guanyu, et al.
Published: (2024)

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
by: Zheng, Kening, et al.
Published: (2024)

ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
by: Ma, Huipeng, et al.
Published: (2026)

DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
by: Yan, Yibo, et al.
Published: (2025)

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
by: Zheng, Kening, et al.
Published: (2026)

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
by: Jia, Sihang, et al.
Published: (2026)

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
by: Zhang, Jianghangfan, et al.
Published: (2025)

PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
by: Huo, Jiahao, et al.
Published: (2025)

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
by: Huo, Jiahao, et al.
Published: (2026)

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
by: Huo, Jiahao, et al.
Published: (2026)

HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge
by: Huang, Sirui, et al.
Published: (2025)

Reasoning Factual Knowledge in Structured Data with Large Language Models
by: Huang, Sirui, et al.
Published: (2024)

Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models
by: Wang, Bo, et al.
Published: (2026)

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
by: Su, Jiamin, et al.
Published: (2025)

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
by: Dang, Yunkai, et al.
Published: (2024)

Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis
by: Li, Junzhuo, et al.
Published: (2025)

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
by: Yan, Yibo, et al.
Published: (2025)

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
by: Yan, Yibo, et al.
Published: (2026)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
by: Wang, Xu, et al.
Published: (2025)

KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues
by: Chen, Junhao, et al.
Published: (2025)

Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
by: Gu, Yanggan, et al.
Published: (2025)

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
by: Yan, Yibo, et al.
Published: (2024)

Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
by: Liu, Jiahao, et al.
Published: (2025)

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
by: Yan, Yibo, et al.
Published: (2024)

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
by: Pan, Leyi, et al.
Published: (2025)

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring
by: Su, Jiamin, et al.
Published: (2025)

BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering
by: Wang, Haoyu, et al.
Published: (2024)

Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
by: Ling, Zipeng, et al.
Published: (2026)

Knowledge Circuits in Pretrained Transformers
by: Yao, Yunzhi, et al.
Published: (2024)

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
by: Dang, Yunkai, et al.
Published: (2024)

Understanding Language Model Circuits through Knowledge Editing
by: Ge, Huaizhi, et al.
Published: (2024)