Cover Image

How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kuai, Chenchen, Jiang, Jiwan, Zhu, Zihao, Wang, Hao, Wu, Keshu, Li, Zihao, Zhang, Yunlong, Liu, Chenxi, Tu, Zhengzhong, Fan, Zhiwen, Zhou, Yang
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
by: Wu, Keshu, et al.
Published: (2026)

CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation
by: Kuai, Chenchen, et al.
Published: (2025)

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving
by: Tian, Kexin, et al.
Published: (2025)

U.S. Port Disruptions under Tropical Cyclones: Resilience Analysis by Harnessing Multiple-Source Dataset
by: Kuai, Chenchen, et al.
Published: (2025)

Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen
by: Li, Zihao, et al.
Published: (2025)

Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement
by: Wu, Keshu, et al.
Published: (2026)

HeadsUp! High-Fidelity Portrait Image Super-Resolution
by: Li, Renjie, et al.
Published: (2025)

Unveiling Traffic Wave of Linear Adaptive Cruise Control: A Second-order Macroscopic Traffic Flow Model
by: Li, Zihao, et al.
Published: (2026)

Automated Vehicles Should be Connected with Natural Language
by: Gao, Xiangbo, et al.
Published: (2025)

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding
by: Li, Renjie, et al.
Published: (2025)

Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
by: Kuai, Chenchen, et al.
Published: (2025)

Virtual Roads, Smarter Safety: A Digital Twin Framework for Mixed Autonomous Traffic Safety Analysis
by: Zhang, Hao, et al.
Published: (2025)

Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
by: Zhu, Zihao, et al.
Published: (2026)

AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration
by: Gao, Xiangbo, et al.
Published: (2025)

OxEnsemble: Fair Ensembles for Low-Data Classification
by: Rystrøm, Jonathan, et al.
Published: (2025)

Modeling Headway in Heterogeneous and Mixed Traffic Flow: A Statistical Distribution Based on a General Exponential Function
by: Leungbootnak, Natchaphon, et al.
Published: (2025)

STAMP: Scalable Task And Model-agnostic Collaborative Perception
by: Gao, Xiangbo, et al.
Published: (2025)

4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation
by: Zhu, Zihao, et al.
Published: (2026)

AI2-Active Safety: AI-enabled Interaction-aware Active Safety Analysis with Vehicle Dynamics
by: Wu, Keshu, et al.
Published: (2025)

Command Filtered Event‐Triggered Adaptive Tracking Control for Fractional‐Order Nonstrict Feedback System With Unmodeled Dynamics and Input Saturation
by: Xinfeng Zhu, et al.
Published: (2025)

Near‐Infrared Light Catalysis of Carbon Dioxide Reduction by Conjugated Porous Aromatic Frameworks
by: Zihao Wang, et al.
Published: (2025)

Near‐Infrared Light Catalysis of Carbon Dioxide Reduction by Conjugated Porous Aromatic Frameworks
by: Zihao Wang, et al.
Published: (2025)

Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
by: Li, Peiran, et al.
Published: (2026)

Autono: A ReAct-Based Highly Robust Autonomous Agent Framework
by: Wu, Zihao
Published: (2025)

It from ETH: Multi-interval Entanglement and Replica Wormholes from Large-$c$ BCFT Ensemble
by: Geng, Hao, et al.
Published: (2025)

Enhanced Few-Shot Class-Incremental Learning via Ensemble Models
by: Zhu, Mingli, et al.
Published: (2024)

Targeted Synthesis of Interpenetration‐Free Mesoporous Aromatic Frameworks by Manipulating Catalysts as Templates
by: Zihao Wang, et al.
Published: (2024)

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
by: Ding, Zihao, et al.
Published: (2026)

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
by: Yuan, Wenhao, et al.
Published: (2026)

Bhakti: A Lightweight Vector Database Management System for Endowing Large Language Models with Semantic Search Capabilities and Memory
by: Wu, Zihao
Published: (2025)

Annotating and Auditing the Safety Properties of Unsafe Rust
by: Rao, Zihao, et al.
Published: (2025)

Signal Timing Optimization for Mixed Connected Automated Traffic Based on A Markov Delay Approximation
by: Yue, Ximin, et al.
Published: (2025)

Light Statistics from Large Ensembles of Independent Two-level Emitters: Classical or Non-classical?
by: Bojer, M., et al.
Published: (2024)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
by: Zhu, Tinghui, et al.
Published: (2024)

Warning of Financial Information Anomalies of Listed Companies Based on the Improved LightGBM Algorithm
by: Ke Li, et al.
Published: (2025)

LangCoop: Collaborative Driving with Language
by: Gao, Xiangbo, et al.
Published: (2025)

Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance
by: Yang, Fengze, et al.
Published: (2025)

Artificial Intelligence for Quantum Error Correction: A Comprehensive Review
by: Wang, Zihao, et al.
Published: (2024)

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models
by: Xu, Zihao, et al.
Published: (2026)

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
by: Guo, Yanpei, et al.
Published: (2026)