Cover Image

Causal Path Alignment: Anchoring the Optimization Trajectory for Controllable In-Parameter Knowledge Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xiyu, Liu, Zhengxiao, Gu, Naibin, Lin, Zheng, Wang, Weiping
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

Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models
by: Liu, Xiyu, et al.
Published: (2026)

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
by: Liu, Xiyu, et al.
Published: (2024)

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
by: Gu, Naibin, et al.
Published: (2024)

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
by: Gu, Naibin, et al.
Published: (2025)

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
by: Zhao, Jiaxuan, et al.
Published: (2025)

Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?
by: Wang, Yatong, et al.
Published: (2026)

BeamLoRA: Beam-Constraint Low-Rank Adaptation
by: Gu, Naibin, et al.
Published: (2025)

Advantageous Parameter Expansion Training Makes Better Large Language Models
by: Gu, Naibin, et al.
Published: (2025)

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts
by: Feng, Yuchen, et al.
Published: (2025)

Weights-Rotated Preference Optimization for Large Language Models
by: Yang, Chenxu, et al.
Published: (2025)

Orthogonal Finetuning for Direct Preference Optimization
by: Yang, Chenxu, et al.
Published: (2024)

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
by: Zong, Qing, et al.
Published: (2024)

Self-Distilled RLVR
by: Yang, Chenxu, et al.
Published: (2026)

LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation
by: Li, Jinze, et al.
Published: (2026)

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
by: Lyu, Sicheng, et al.
Published: (2025)

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
by: Chen, Hao, et al.
Published: (2025)

EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
by: Cao, Pengfei, et al.
Published: (2025)

Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
by: Gu, Naibin, et al.
Published: (2025)

System 1&2 Synergy via Dynamic Model Interpolation
by: Yang, Chenxu, et al.
Published: (2026)

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
by: Yao, Dingyu, et al.
Published: (2025)

FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
by: Wang, Peng, et al.
Published: (2026)

Knowledge Editing through Chain-of-Thought
by: Wang, Changyue, et al.
Published: (2024)

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
by: Zhong, Haitian, et al.
Published: (2025)

EAMET: Robust Massive Model Editing via Embedding Alignment Optimization
by: Dai, Yanbo, et al.
Published: (2025)

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
by: Lu, Yifan, et al.
Published: (2024)

Knowledge Editing for Large Language Models: A Survey
by: Wang, Song, et al.
Published: (2023)

Anchored Alignment for Self-Explanations Enhancement
by: Villa-Arenas, Luis Felipe, et al.
Published: (2024)

Cross-modal Causal Relation Alignment for Video Question Grounding
by: Chen, Weixing, et al.
Published: (2025)

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
by: Liu, Jiateng, et al.
Published: (2024)

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
by: Zhang, Taolin, et al.
Published: (2026)

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
by: Liu, Qin, et al.
Published: (2024)

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
by: Xie, Jiakuan, et al.
Published: (2025)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
by: Wang, Changyue, et al.
Published: (2025)

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
by: D'Oosterlinck, Karel, et al.
Published: (2024)

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
by: Zheng, Jiamu, et al.
Published: (2024)

Advancing Parameter Efficiency in Fine-tuning via Representation Editing
by: Wu, Muling, et al.
Published: (2024)

Neighboring Perturbations of Knowledge Editing on Large Language Models
by: Ma, Jun-Yu, et al.
Published: (2024)

ScEdit: Script-based Assessment of Knowledge Editing
by: Li, Xinye, et al.
Published: (2025)

Learning to Edit: Aligning LLMs with Knowledge Editing
by: Jiang, Yuxin, et al.
Published: (2024)

Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models
by: Zheng, Jiasen, et al.
Published: (2025)