Buchumschlag

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yang, Jingyuan, Chen, Dapeng, Sun, Yajing, Li, Rongjun, Feng, Zhiyong, Peng, Wei
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models
von: Yang, Jingyuan, et al.
Veröffentlicht: (2025)

Gradient Co-occurrence Analysis for Detecting Unsafe Prompts in Large Language Models
von: Yang, Jingyuan, et al.
Veröffentlicht: (2025)

A Survey on Hallucination in Large Vision-Language Models
von: Liu, Hanchao, et al.
Veröffentlicht: (2024)

Crafting Large Language Models for Enhanced Interpretability
von: Sun, Chung-En, et al.
Veröffentlicht: (2024)

DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models
von: Zheng, Lifan, et al.
Veröffentlicht: (2026)

Robust and Scalable Model Editing for Large Language Models
von: Chen, Yingfa, et al.
Veröffentlicht: (2024)

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
von: Ding, Peng, et al.
Veröffentlicht: (2025)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
von: Zhang, Mengqi, et al.
Veröffentlicht: (2024)

Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach
von: Zhang, Renhan, et al.
Veröffentlicht: (2025)

Knowledge Graph Enhanced Large Language Model Editing
von: Zhang, Mengqi, et al.
Veröffentlicht: (2024)

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
von: Knappe, Tim, et al.
Veröffentlicht: (2024)

LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
von: Sun, Yizheng, et al.
Veröffentlicht: (2025)

KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
von: Guo, Tiezheng, et al.
Veröffentlicht: (2023)

Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
von: Li, Andrew, et al.
Veröffentlicht: (2024)

Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis
von: Li, Kunrong, et al.
Veröffentlicht: (2025)

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
von: Wang, Weixuan, et al.
Veröffentlicht: (2024)

WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge
von: Chen, Jingyuan, et al.
Veröffentlicht: (2025)

STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models
von: Jeong, Geunyeong, et al.
Veröffentlicht: (2025)

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
von: Zhang, Yuanchi, et al.
Veröffentlicht: (2024)

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
von: Gu, Jia-Chen, et al.
Veröffentlicht: (2024)

Interpreting Bias in Large Language Models: A Feature-Based Approach
von: Prakash, Nirmalendu, et al.
Veröffentlicht: (2024)

Semantic Consistency for Assuring Reliability of Large Language Models
von: Raj, Harsh, et al.
Veröffentlicht: (2023)

Enhancing Data Privacy in Large Language Models through Private Association Editing
von: Venditti, Davide, et al.
Veröffentlicht: (2024)

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
von: Wang, Qidong, et al.
Veröffentlicht: (2025)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
von: Wang, Jingyuan, et al.
Veröffentlicht: (2025)

Precision Knowledge Editing: Enhancing Safety in Large Language Models
von: Li, Xuying, et al.
Veröffentlicht: (2024)

Is Large Language Model Good at Triple Set Prediction? An Empirical Study
von: Yuan, Yuan, et al.
Veröffentlicht: (2024)

Evaluating the Generation Capabilities of Large Chinese Language Models
von: Zeng, Hui, et al.
Veröffentlicht: (2023)

Stable Knowledge Editing in Large Language Models
von: Wei, Zihao, et al.
Veröffentlicht: (2024)

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
von: Hsueh, Cheng-Hsun, et al.
Veröffentlicht: (2024)

Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow
von: Zhou, Ziyu, et al.
Veröffentlicht: (2025)

Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
von: Li, Yun, et al.
Veröffentlicht: (2025)

Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
von: Wang, Jianing, et al.
Veröffentlicht: (2024)

Benchmarking and Rethinking Knowledge Editing for Large Language Models
von: He, Guoxiu, et al.
Veröffentlicht: (2025)

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
von: Khan, Mohammad Aflah, et al.
Veröffentlicht: (2025)

Consistency-Aware Editing for Entity-level Unlearning in Language Models
von: Han, Xiaoqi, et al.
Veröffentlicht: (2025)

Uncovering Overfitting in Large Language Model Editing
von: Zhang, Mengqi, et al.
Veröffentlicht: (2024)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
von: Liu, Shuliang, et al.
Veröffentlicht: (2025)

Making Large Language Models Perform Better in Knowledge Graph Completion
von: Zhang, Yichi, et al.
Veröffentlicht: (2023)

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking
von: Dong, Ming, et al.
Veröffentlicht: (2024)