Imagen de Portada

Diagnosing CFG Interpretation in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Hanqi, Chen, Lu, Yu, Kai
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models
por: Zheng, Yingming, et al.
Publicado: (2025)

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
por: Chang, Jinho, et al.
Publicado: (2024)

EP-CFG: Energy-Preserving Classifier-Free Guidance
por: Zhang, Kai, et al.
Publicado: (2024)

P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
por: Peng, Xin, et al.
Publicado: (2026)

CFG-OEC: Classifier Free Guidance with Orthogonal Error Correction
por: Yang, Nakgyu, et al.
Publicado: (2025)

Evolving Subnetwork Training for Large Language Models
por: Li, Hanqi, et al.
Publicado: (2024)

EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
por: Jin, Hyundong, et al.
Publicado: (2026)

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
por: Tang, Jing, et al.
Publicado: (2026)

TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews
por: Duan, Hanqi, et al.
Publicado: (2026)

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
por: Chung, Hyungjin, et al.
Publicado: (2024)

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

MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation
por: Kim, Byungjun, et al.
Publicado: (2026)

LLMs for Coding and Robotics Education
por: Shu, Peng, et al.
Publicado: (2024)

CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
por: Skelic, Lejla, et al.
Publicado: (2025)

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making
por: Son, Yejin, et al.
Publicado: (2025)

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles
por: Yan, Lu, et al.
Publicado: (2026)

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression
por: Xiao, Hanqi, et al.
Publicado: (2025)

Can Large Language Models Act as Ensembler for Multi-GNNs?
por: Duan, Hanqi, et al.
Publicado: (2024)

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
por: Yang, Zhen, et al.
Publicado: (2026)

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
por: Liu, Junhao, et al.
Publicado: (2025)

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
por: Zhong, Tianyun, et al.
Publicado: (2024)

ReLE: A Scalable System and Structured Benchmark for Diagnosing Capability Anisotropy in Chinese LLMs
por: Fang, Rui, et al.
Publicado: (2026)

Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
por: Bobe III, Frank, et al.
Publicado: (2026)

Rethinking industrial artificial intelligence: a unified foundation framework
por: Lee, Jay, et al.
Publicado: (2025)

Machine Learning Approaches for Diagnostics and Prognostics of Industrial Systems Using Open Source Data from PHM Data Challenges: A Review
por: Su, Hanqi, et al.
Publicado: (2023)

A Unified Industrial Large Knowledge Model Framework in Industry 4.0 and Smart Manufacturing
por: Lee, Jay, et al.
Publicado: (2023)

Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs
por: Wang, Yifan, et al.
Publicado: (2025)

Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
por: Zhang, Situo, et al.
Publicado: (2025)

LLMs in Interpreting Legal Documents
por: Corbo, Simone
Publicado: (2025)

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?
por: Rouillard, Amy, et al.
Publicado: (2026)

HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
por: Jin, Chao, et al.
Publicado: (2026)

Playing Language Game with LLMs Leads to Jailbreaking
por: Peng, Yu, et al.
Publicado: (2024)

NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering
por: Cao, Ruisheng, et al.
Publicado: (2025)

From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration
por: Mantiuk, Fryderyk, et al.
Publicado: (2025)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
por: Bai, Yuzhuo, et al.
Publicado: (2026)

Geometric Decoupling: Diagnosing the Structural Instability of Latent
por: Liang, Yuanbang, et al.
Publicado: (2026)

Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
por: Dubey, Shivam
Publicado: (2025)

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity
por: An, Hongjun, et al.
Publicado: (2026)

Confidence as a Reward: Transforming LLMs into Reward Models
por: Du, He, et al.
Publicado: (2025)

HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs
por: Meng, Chang-Chih, et al.
Publicado: (2026)