Cover Image

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhuoyun, Wang, Boxuan, Hu, Jinwei, Huang, Xiaowei, Dong, Yi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
by: Li, Zhuoyun, et al.
Published: (2026)

Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models
by: Arakelyan, Erik, et al.
Published: (2024)

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
by: Martra, Pere
Published: (2025)

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2026)

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
by: Wang, Boxuan, et al.
Published: (2026)

Trust-Oriented Adaptive Guardrails for Large Language Models
by: Hu, Jinwei, et al.
Published: (2024)

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
by: Poppi, Samuele, et al.
Published: (2024)

On The Fragility of Benchmark Contamination Detection in Reasoning Models
by: Wang, Han, et al.
Published: (2025)

Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks
by: Wang, Boxuan, et al.
Published: (2025)

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
by: Wang, Boxuan, et al.
Published: (2025)

ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models
by: Zhao, Zhixue, et al.
Published: (2024)

StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
by: Zheng, Guantian
Published: (2026)

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
by: Liu, Zhining, et al.
Published: (2026)

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
by: Ao, Shuang, et al.
Published: (2025)

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
by: Korbak, Tomek, et al.
Published: (2025)

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs
by: Vijayaraj, Raj Krishnan
Published: (2025)

Tool Learning with Foundation Models
by: Qin, Yujia, et al.
Published: (2023)

TruthFlow: Truthful LLM Generation via Representation Flow Correction
by: Wang, Hanyu, et al.
Published: (2025)

Weaver: Foundation Models for Creative Writing
by: Wang, Tiannan, et al.
Published: (2024)

Clarify: Improving Model Robustness With Natural Language Corrections
by: Lee, Yoonho, et al.
Published: (2024)

Parameter-Efficient Fine-Tuning for Foundation Models
by: Zhang, Dan, et al.
Published: (2025)

A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs
by: Rahman, Roussel, et al.
Published: (2025)

Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems
by: Hu, Jinwei, et al.
Published: (2025)

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
by: Huang, Jing, et al.
Published: (2025)

MIO: A Foundation Model on Multimodal Tokens
by: Wang, Zekun, et al.
Published: (2024)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
by: Zhang, Boxuan, et al.
Published: (2025)

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
by: Li, Jin, et al.
Published: (2025)

Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets
by: Vourganas, Ioannis J., et al.
Published: (2026)

On the Fragility of Data Attribution When Learning Is Distributed
by: Gao, Xian, et al.
Published: (2026)

Automated Capability Discovery via Foundation Model Self-Exploration
by: Lu, Cong, et al.
Published: (2025)

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
by: Lu, Cong, et al.
Published: (2024)

Towards Trustable Language Models: Investigating Information Quality of Large Language Models
by: Rejeleene, Rick, et al.
Published: (2024)

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
by: Zhang, Pingyue, et al.
Published: (2026)

Open World Knowledge Aided Single-Cell Foundation Model with Robust Cross-Modal Cell-Language Pre-training
by: Wang, Haoran, et al.
Published: (2026)

Conditional Adversarial Fragility in Financial Machine Learning under Macroeconomic Stress
by: Baviskar, Samruddhi
Published: (2025)

On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations
by: Lei, Haoyu, et al.
Published: (2026)

How Fragile is Relation Extraction under Entity Replacements?
by: Wang, Yiwei, et al.
Published: (2023)

Apple Intelligence Foundation Language Models
by: Gunter, Tom, et al.
Published: (2024)

Provable Length Generalization in Sequence Prediction via Spectral Filtering
by: Marsden, Annie, et al.
Published: (2024)

Variational Language Concepts for Interpreting Foundation Language Models
by: Wang, Hengyi, et al.
Published: (2024)