Copertina

Understanding Knowledge Drift in LLMs through Misinformation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fastowski, Alina, Kasneci, Gjergji
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

From Confidence to Collapse in LLM Factual Robustness
di: Fastowski, Alina, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

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

Entry Dependent Expert Selection in Distributed Gaussian Processes Using Multilabel Classification
di: Jalali, Hamed, et al.
Pubblicazione: (2022)

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

Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule
di: Zhao, Xuan, et al.
Pubblicazione: (2024)

Learn and Unlearn: Addressing Misinformation in Multilingual LLMs
di: Lu, Taiming, et al.
Pubblicazione: (2024)

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

Mitigating Semantic Drift: Evaluating LLMs' Efficacy in Psychotherapy through MI Dialogue Summarization
di: Kumar, Vivek, et al.
Pubblicazione: (2025)

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

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

XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs
di: Xiao, Yuzhuo, et al.
Pubblicazione: (2025)

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
di: Thede, Lukas, et al.
Pubblicazione: (2025)

Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
di: Guo, Ruohao, et al.
Pubblicazione: (2023)

Understanding Chain-of-Thought in LLMs through Information Theory
di: Ton, Jean-Francois, et al.
Pubblicazione: (2024)

Benchmarking Large Language Models for Math Reasoning Tasks
di: Seßler, Kathrin, et al.
Pubblicazione: (2024)

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

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

DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
di: Tyagi, Abhishek, et al.
Pubblicazione: (2026)

TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data
di: Berti, Leonardo, et al.
Pubblicazione: (2025)

Understanding Finetuning for Factual Knowledge Extraction
di: Ghosal, Gaurav, et al.
Pubblicazione: (2024)

SoK: Machine Learning for Misinformation Detection
di: Xiao, Madelyne, et al.
Pubblicazione: (2023)

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
di: Qi, Yanlin, et al.
Pubblicazione: (2026)

Benchmarking and Understanding Compositional Relational Reasoning of LLMs
di: Ni, Ruikang, et al.
Pubblicazione: (2024)

I Prefer not to Say: Protecting User Consent in Models with Optional Personal Data
di: Leemann, Tobias, et al.
Pubblicazione: (2022)

Persuasion Tokens for Editing Factual Knowledge in LLMs
di: Youssef, Paul, et al.
Pubblicazione: (2026)

Grounding Multilingual Multimodal LLMs With Cultural Knowledge
di: Nyandwi, Jean de Dieu, et al.
Pubblicazione: (2025)

Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
di: Yuan, Chenchen, et al.
Pubblicazione: (2026)

Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications
di: Speicher, Till, et al.
Pubblicazione: (2024)

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
di: Cha, Sungmin, et al.
Pubblicazione: (2024)

Efficient Knowledge Injection in LLMs via Self-Distillation
di: Kujanpää, Kalle, et al.
Pubblicazione: (2024)