CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing
cs.LG
Submitted: 2026-03-11
Updated: 2026-11-05
Code: https://github.com/manitbaser/CLaRE
Terminology
Sources
- ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphs
- Scalable Influence and Fact Tracing for Large Language Model Pretraining
- What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
- A Unified Framework for Model Editing
- From Deception to Detection: The Dual Roles of Large Language Models in Fake News
- Foundation Models for Decision Making: Problems, Methods, and Opportunities
- Disentangling Knowledge Representations for Large Language Model Editing
- A Comprehensive Study of Knowledge Editing for Large Language Models
- A Survey of Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis