Copertina

From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liew, Yee Zhing, Tan, Andrew Huey Ping, Majeed, Anwar P. P. Abdul
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Randomness and Interpolation Improve Gradient Descent
di: Li, Jiawen, et al.
Pubblicazione: (2025)

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
di: Sawczyn, Albert, et al.
Pubblicazione: (2025)

FactCHD: Benchmarking Fact-Conflicting Hallucination Detection
di: Chen, Xiang, et al.
Pubblicazione: (2023)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
di: Pan, Jiachun, et al.
Pubblicazione: (2023)

Machine Learning Risk Intelligence for Green Hydrogen Investment: Insights for Duqm R3 Auction
di: Nwafor, Obumneme, et al.
Pubblicazione: (2025)

Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts
di: Gupta, Raavi, et al.
Pubblicazione: (2025)

A Function-Centric Perspective on Flat and Sharp Minima
di: Mason-Williams, Israel, et al.
Pubblicazione: (2025)

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
di: Chen, Shiqi, et al.
Pubblicazione: (2024)

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
di: Luo, Haocheng, et al.
Pubblicazione: (2025)

From Flows to Words: Can Zero-/Few-Shot LLMs Detect Network Intrusions? A Grammar-Constrained, Calibrated Evaluation on UNSW-NB15
di: Rehman, Mohammad Abdul, et al.
Pubblicazione: (2025)

A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimization
di: Li, Tianle, et al.
Pubblicazione: (2025)

Improved Crop and Weed Detection with Diverse Data Ensemble Learning
di: Asad, Muhammad Hamza, et al.
Pubblicazione: (2023)

Artificial Intelligence for Green Hydrogen Yield Prediction and Site Suitability using SHAP-Based Composite Index: Focus on Oman
di: Nwafor, Obumneme Zimuzor, et al.
Pubblicazione: (2025)

DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
di: Liu, Junkang, et al.
Pubblicazione: (2025)

Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models
di: Rahman, Subhey Sadi, et al.
Pubblicazione: (2025)

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
di: Vu, Minh, et al.
Pubblicazione: (2025)

X-SAM: Boosting Sharpness-Aware Minimization with Dominant-Eigenvector Gradient Correction
di: Duan, Hongru, et al.
Pubblicazione: (2026)

In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs
di: Clemente, Simone, et al.
Pubblicazione: (2025)

FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models
di: Tan, Likun, et al.
Pubblicazione: (2025)

Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector
di: Agand, Pedram
Pubblicazione: (2026)

Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning
di: Wahab, Abdul, et al.
Pubblicazione: (2026)

Halfway Escape Optimization: A Quantum-Inspired Solution for General Optimization Problems
di: Li, Jiawen, et al.
Pubblicazione: (2024)

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
di: Ettori, Davide
Pubblicazione: (2026)

Tractable Sharpness-Aware Learning of Probabilistic Circuits
di: Suresh, Hrithik, et al.
Pubblicazione: (2025)

Nutrition Facts, Drug Facts, and Model Facts: Putting AI Ethics into Practice in Gun Violence Research
di: Zhu, Jessica, et al.
Pubblicazione: (2024)

Innovation: An Almost Characterization of Hallucination
di: Das, Nishant P., et al.
Pubblicazione: (2026)

Bolster Hallucination Detection via Prompt-Guided Data Augmentation
di: Li, Wenyun, et al.
Pubblicazione: (2025)

Hallucination Detection via Activations of Open-Weight Proxy Analyzers
di: Singh, Akshita, et al.
Pubblicazione: (2026)

Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
di: Deng, Yongxin, et al.
Pubblicazione: (2026)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
di: Gu, Yujie, et al.
Pubblicazione: (2026)

ColA: Collaborative Adaptation with Gradient Learning
di: Diao, Enmao, et al.
Pubblicazione: (2024)

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
di: Suresh, Praneet, et al.
Pubblicazione: (2025)

Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook
di: Ibrahimov, Yusif, et al.
Pubblicazione: (2024)

Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy
di: Tan, Chengli, et al.
Pubblicazione: (2024)

Principled Detection of Hallucinations in Large Language Models via Multiple Testing
di: Li, Jiawei, et al.
Pubblicazione: (2025)

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models
di: Jang, Doohyuk, et al.
Pubblicazione: (2025)

What do Geometric Hallucination Detection Metrics Actually Measure?
di: Yeats, Eric, et al.
Pubblicazione: (2026)

Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
di: Tan, Chengli, et al.
Pubblicazione: (2025)

Are Flat Minima an Illusion?
di: Bennett, Michael Timothy
Pubblicazione: (2026)

From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs
di: Joshi, Ratnesh Kumar, et al.
Pubblicazione: (2024)