From Confidence to Collapse in LLM Factual Robustness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fastowski, Alina, Prenkaj, Bardh, Kasneci, Gjergji
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
by: Fastowski, Alina, et al.
Published: (2025)

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
by: Kocak, Aysenur, et al.
Published: (2025)

Analysing the Safety Pitfalls of Steering Vectors
by: Li, Yuxiao, et al.
Published: (2026)

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
by: Leemann, Tobias, et al.
Published: (2024)

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
by: Yuan, Chenchen, et al.
Published: (2025)

Understanding Knowledge Drift in LLMs through Misinformation
by: Fastowski, Alina, et al.
Published: (2024)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
by: Yuan, Chenchen, et al.
Published: (2026)

RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
by: Yang, Shuo, et al.
Published: (2024)

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs
by: Yang, Shuo, et al.
Published: (2025)

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
by: Zhang, Zheyu, et al.
Published: (2026)

Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
by: Zhang, Zheyu, et al.
Published: (2025)

Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
by: Yang, Shuo, et al.
Published: (2024)

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
by: Kirchhof, Michael, et al.
Published: (2025)

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
by: Yang, Shuo, et al.
Published: (2025)

Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
by: Kasneci, Enkelejda, et al.
Published: (2026)

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
by: Dhaini, Mahdi, et al.
Published: (2025)

Emergent Abilities in Large Language Models: A Survey
by: Berti, Leonardo, et al.
Published: (2025)

Graph Inverse Style Transfer for Counterfactual Explainability
by: Prenkaj, Bardh, et al.
Published: (2025)

Reinforcement Unlearning via Group Relative Policy Optimization
by: Zaradoukas, Efstratios, et al.
Published: (2026)

Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges
by: Dhaini, Mahdi, et al.
Published: (2025)

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
by: Dhaini, Mahdi, et al.
Published: (2025)

Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers
by: Kasneci, Gjergji, et al.
Published: (2024)

EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
by: Dhaini, Mahdi, et al.
Published: (2025)

TabSCM: A practical Framework for Generating Realistic Tabular Data
by: Jacob, Sven, et al.
Published: (2026)

Towards Non-Adversarial Algorithmic Recourse
by: Leemann, Tobias, et al.
Published: (2024)

SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation
by: Yang, Shuo, et al.
Published: (2026)

TRADES: Generating Realistic Market Simulations with Diffusion Models
by: Berti, Leonardo, et al.
Published: (2025)

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
by: Abramov, Roman, et al.
Published: (2025)

Permutation-Consensus Listwise Judging for Robust Factuality Evaluation
by: Huang, Tianyi, et al.
Published: (2026)

InFact: Informativeness Alignment for Improved LLM Factuality
by: Cohen, Roi, et al.
Published: (2025)

Robust Stochastic Graph Generator for Counterfactual Explanations
by: Prado-Romero, Mario Alfonso, et al.
Published: (2023)

Consolidating Rewarded Perturbations for LLM Post-Training
by: Zhang, Zheyu, et al.
Published: (2026)

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
by: Jiao, Rui, et al.
Published: (2025)

DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
by: Huang, Minghui
Published: (2025)

Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
by: Li, Yifei, et al.
Published: (2026)

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
by: He, Jinwen, et al.
Published: (2023)

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses
by: Kim, Juyeon, et al.
Published: (2024)

AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
by: Ni, Jingwei, et al.
Published: (2024)

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
by: Ramprasad, Sanjana, et al.
Published: (2024)

Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation
by: Gong, Ziwei, et al.
Published: (2026)