Cover Image

Diagnosing CFG Interpretation in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hanqi, Chen, Lu, Yu, Kai
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

LLMs in Interpreting Legal Documents
by: Corbo, Simone
Published: (2025)

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

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

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

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

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

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

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

Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs
by: Dubey, Shivam
Published: (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
by: An, Hongjun, et al.
Published: (2026)

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

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