Cover Image

Why Does New Knowledge Create Messy Ripple Effects in LLMs?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Jiaxin, Zhang, Zixuan, Li, Manling, Yu, Pengfei, Ji, Heng
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains
by: Dong, Zilu, et al.
Published: (2025)

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
by: Yuan, Lifan, et al.
Published: (2023)

RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning
by: Zhao, Zihao, et al.
Published: (2024)

Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
by: Li, Shanghao, et al.
Published: (2026)

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
by: Zhang, Zixuan, et al.
Published: (2024)

Can Large Language Models Create New Knowledge for Spatial Reasoning Tasks?
by: Greatrix, Thomas, et al.
Published: (2024)

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders
by: Li, Cheng, et al.
Published: (2024)

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
by: Guo, Xuehang, et al.
Published: (2025)

AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
by: Huang, Haoyu, et al.
Published: (2025)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
by: Öncel, Fırat, et al.
Published: (2024)

Why are LLMs' abilities emergent?
by: Havlík, Vladimír
Published: (2025)

Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
by: Li, Yanhong, et al.
Published: (2025)

Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
by: Choi, Minje, et al.
Published: (2023)

Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
by: Pan, Zhenyu, et al.
Published: (2024)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
by: Weng, Zixuan, et al.
Published: (2025)

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
by: Xu, Ruiling, et al.
Published: (2025)

On Psychology of AI -- Does Primacy Effect Affect ChatGPT and Other LLMs?
by: Hämäläinen, Mika
Published: (2025)

Unveiling the Competitive Dynamics: A Comparative Evaluation of American and Chinese LLMs
by: Jiang, Zhenhui, et al.
Published: (2024)

Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It
by: Qin, Yulu, et al.
Published: (2025)

Word Embeddings Are Steers for Language Models
by: Han, Chi, et al.
Published: (2023)

Generative Ontology: When Structured Knowledge Learns to Create
by: Cheung, Benny
Published: (2026)

Visually Descriptive Language Model for Vector Graphics Reasoning
by: Wang, Zhenhailong, et al.
Published: (2024)

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
by: Pan, Wenbo, et al.
Published: (2025)

Multimedia Generative Script Learning for Task Planning
by: Wang, Qingyun, et al.
Published: (2022)

Look Within, Why LLMs Hallucinate: A Causal Perspective
by: Li, He, et al.
Published: (2024)

Why Misinformation is Created? Detecting them by Integrating Intent Features
by: Wang, Bing, et al.
Published: (2024)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
by: Li, Aochong Oliver, et al.
Published: (2025)

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
by: Ning, Xuefei, et al.
Published: (2023)

Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
by: Tan, Nelvin, et al.
Published: (2025)

GAOKAO-Eval: Does high scores truly reflect strong capabilities in LLMs?
by: Lei, Zhikai, et al.
Published: (2024)

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
by: Zhou, Yuxuan, et al.
Published: (2025)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
by: Xiong, Kai, et al.
Published: (2024)

GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving
by: Zhang, Jiaxin, et al.
Published: (2024)

Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
by: Zhang, Zhihao, et al.
Published: (2025)

Memorization and Knowledge Injection in Gated LLMs
by: Pan, Xu, et al.
Published: (2025)

Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
by: Zhang, Yichi, et al.
Published: (2023)

Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements
by: Liang, Yiming, et al.
Published: (2025)

Can LLMs be Good Graph Judge for Knowledge Graph Construction?
by: Huang, Haoyu, et al.
Published: (2024)

Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
by: He, Qianxi, et al.
Published: (2025)

Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation
by: Chen, Rubing, et al.
Published: (2024)