Cover Image

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Qingcheng, Jin, Mingyu, Yu, Qinkai, Wang, Zhenting, Hua, Wenyue, Zhou, Zihao, Sun, Guangyan, Meng, Yanda, Ma, Shiqing, Wang, Qifan, Juefei-Xu, Felix, Ding, Kaize, Yang, Fan, Tang, Ruixiang, Zhang, Yongfeng
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
by: Jin, Mingyu, et al.
Published: (2024)

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System
by: Yu, Qinkai, et al.
Published: (2024)

The Impact of Reasoning Step Length on Large Language Models
by: Jin, Mingyu, et al.
Published: (2024)

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
by: Lin, Sam, et al.
Published: (2024)

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
by: Shi, Zeru, et al.
Published: (2026)

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
by: Tang, Hua, et al.
Published: (2024)

Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers
by: Wu, Haoyu, et al.
Published: (2025)

ADO: Automatic Data Optimization for Inputs in LLM Prompts
by: Lin, Sam, et al.
Published: (2025)

TrustAgent: Towards Safe and Trustworthy LLM-based Agents
by: Hua, Wenyue, et al.
Published: (2024)

Disentangling Memory and Reasoning Ability in Large Language Models
by: Jin, Mingyu, et al.
Published: (2024)

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
by: Shi, Zeru, et al.
Published: (2025)

Visual Agents as Fast and Slow Thinkers
by: Sun, Guangyan, et al.
Published: (2024)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
by: Ge, Huaizhi, et al.
Published: (2024)

Tackling Fake Forgetting through Uncertainty Quantification
by: Shi, Yingdan, et al.
Published: (2025)

Uncertainty-Aware Robust Learning on Noisy Graphs
by: Chen, Shuyi, et al.
Published: (2023)

Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model
by: Tang, Yanchuan, et al.
Published: (2026)

Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient
by: Shi, Zeru, et al.
Published: (2024)

TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
by: Zeng, Runjia, et al.
Published: (2026)

OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems
by: Xu, Shuyuan, et al.
Published: (2023)

Data-centric NLP Backdoor Defense from the Lens of Memorization
by: Wang, Zhenting, et al.
Published: (2024)

Toward Equitable Access: Leveraging Crowdsourced Reviews to Investigate Public Perceptions of Health Resource Accessibility
by: Xue, Zhaoqian, et al.
Published: (2025)

RAPTOR: Ridge-Adaptive Logistic Probes
by: Gao, Ziqi, et al.
Published: (2026)

MoralBench: Moral Evaluation of LLMs
by: Ji, Jianchao, et al.
Published: (2024)

Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?
by: Xu, Qipan, et al.
Published: (2025)

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes
by: Fan, Lizhou, et al.
Published: (2023)

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
by: Li, Zelong, et al.
Published: (2024)

Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models
by: Huang, Yuheng, et al.
Published: (2023)

StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors
by: Yu, Qinkai, et al.
Published: (2026)

Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
by: Zhang, Dong-Xiao, et al.
Published: (2026)

$α$-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction
by: Su, Sanbao, et al.
Published: (2024)

When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
by: Zhang, Chong, et al.
Published: (2024)

HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification
by: Wang, Ziqing, et al.
Published: (2026)

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
by: Wu, Rui, et al.
Published: (2025)

Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
by: Zhang, Boxuan, et al.
Published: (2026)

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents
by: Xue, Zhaoqian, et al.
Published: (2024)

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
by: Hua, Wenyue, et al.
Published: (2024)

Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression Recognition
by: Liu, Hanwei, et al.
Published: (2024)

PAP-REC: Personalized Automatic Prompt for Recommendation Language Model
by: Li, Zelong, et al.
Published: (2024)

UP5: Unbiased Foundation Model for Fairness-aware Recommendation
by: Hua, Wenyue, et al.
Published: (2023)

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
by: Hua, Wenyue, et al.
Published: (2024)