Cover Image

Unveiling the Basin-Like Loss Landscape in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Huanran, Dong, Yinpeng, Wei, Zeming, Huang, Yao, Zhang, Yichi, Su, Hang, Zhu, Jun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards the Worst-case Robustness of Large Language Models
by: Chen, Huanran, et al.
Published: (2025)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

Scaling Laws for Black box Adversarial Attacks
by: Liu, Chuan, et al.
Published: (2024)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
by: Zhang, Yichi, et al.
Published: (2024)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
by: Chen, Huanran, et al.
Published: (2026)

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
by: Zhang, Yichi, et al.
Published: (2024)

Alignment Dynamics in LLM Fine-Tuning
by: Huang, Yuhan, et al.
Published: (2026)

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
by: Wu, Chengcan, et al.
Published: (2025)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
by: Chen, Huanran, et al.
Published: (2024)

Robust Classification via a Single Diffusion Model
by: Chen, Huanran, et al.
Published: (2023)

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
by: Chen, Huanran, et al.
Published: (2023)

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
by: Zhang, Yichi, et al.
Published: (2025)

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
by: Huang, Yao, et al.
Published: (2025)

On the Duality Between Sharpness-Aware Minimization and Adversarial Training
by: Zhang, Yihao, et al.
Published: (2024)

Decoding Large Language Diffusion Models with Foreseeing Movement
by: Mo, Yichuan, et al.
Published: (2025)

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
by: Zhang, Yihao, et al.
Published: (2024)

Diffusion Models as Dataset Distillation Priors
by: Su, Duo, et al.
Published: (2025)

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
by: Su, Hang, et al.
Published: (2025)

Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
by: Zhang, Siyuan, et al.
Published: (2026)

On the Hyperparameter Loss Landscapes of Machine Learning Models: An Exploratory Study
by: Huang, Mingyu, et al.
Published: (2023)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
by: Wei, Xingxing, et al.
Published: (2024)

Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
by: Zhang, Yichi, et al.
Published: (2025)

A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models
by: Cai, Yinpeng, et al.
Published: (2025)

Deterministic Differentiable Structured Pruning for Large Language Models
by: Huang, Weiyu, et al.
Published: (2026)

Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
by: Das, Santanu, et al.
Published: (2026)

Improving Full Waveform Inversion in Large Model Era
by: Feng, Yinan, et al.
Published: (2026)

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
by: Zhou, Zhanke, et al.
Published: (2025)

Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
by: Cui, Peng, et al.
Published: (2024)

Automata-Based Steering of Large Language Models for Diverse Structured Generation
by: Luan, Xiaokun, et al.
Published: (2025)

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
by: Zhang, Siyuan, et al.
Published: (2025)

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance
by: Malviya, Pranshu, et al.
Published: (2024)

Noise Contrastive Alignment of Language Models with Explicit Rewards
by: Chen, Huayu, et al.
Published: (2024)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
by: Hu, Xiaomeng, et al.
Published: (2024)

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
by: Kong, Linggang, et al.
Published: (2026)

CrossTrafficLLM: A Human-Centric Framework for Interpretable Traffic Intelligence via Large Language Model
by: Du, Zeming, et al.
Published: (2025)

Unveiling the Pitfalls of Knowledge Editing for Large Language Models
by: Li, Zhoubo, et al.
Published: (2023)

CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
by: Chen, Zhuofan, et al.
Published: (2025)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
by: Kang, Caixin, et al.
Published: (2023)

Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
by: Peng, ShengYun, et al.
Published: (2024)

Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models
by: Wei, Lanning, et al.
Published: (2024)