Copertina

Tracing and Reversing Edits in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Youssef, Paul, Zhao, Zhixue, Seifert, Christin, Schlötterer, Jörg
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How to Make LLMs Forget: On Reversing In-Context Knowledge Edits
di: Youssef, Paul, et al.
Pubblicazione: (2024)

Has this Fact been Edited? Detecting Knowledge Edits in Language Models
di: Youssef, Paul, et al.
Pubblicazione: (2024)

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
di: Cheng, Yinjie, et al.
Pubblicazione: (2025)

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

Position: Editing Large Language Models Poses Serious Safety Risks
di: Youssef, Paul, et al.
Pubblicazione: (2025)

The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
di: Youssef, Paul, et al.
Pubblicazione: (2024)

Enhancing Fact Retrieval in PLMs through Truthfulness
di: Youssef, Paul, et al.
Pubblicazione: (2024)

LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study
di: Nguyen, Van Bach, et al.
Pubblicazione: (2024)

Guiding LLMs to Generate High-Fidelity and High-Quality Counterfactual Explanations for Text Classification
di: Nguyen, Van Bach, et al.
Pubblicazione: (2025)

From Black Boxes to Conversations: Incorporating XAI in a Conversational Agent
di: Nguyen, Van Bach, et al.
Pubblicazione: (2022)

A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Study
di: Koraş, Osman Alperen, et al.
Pubblicazione: (2024)

CEval: A Benchmark for Evaluating Counterfactual Text Generation
di: Nguyen, Van Bach, et al.
Pubblicazione: (2024)

Behavioral Analysis of Information Salience in Large Language Models
di: Trienes, Jan, et al.
Pubblicazione: (2025)

Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support
di: Trienes, Jan, et al.
Pubblicazione: (2025)

An XAI-based Analysis of Shortcut Learning in Neural Networks
di: Le, Phuong Quynh, et al.
Pubblicazione: (2025)

Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?
di: Le, Phuong Quynh, et al.
Pubblicazione: (2023)

InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
di: Trienes, Jan, et al.
Pubblicazione: (2024)

Towards Interpretable Deep Neural Networks for Tabular Data
di: Elhadri, Khawla, et al.
Pubblicazione: (2025)

XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
di: Elhadri, Khawla, et al.
Pubblicazione: (2025)

Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine
di: Eryılmaz, Bahadır, et al.
Pubblicazione: (2024)

Explanation Generation for Contradiction Reconciliation with LLMs
di: Chan, Jason, et al.
Pubblicazione: (2026)

Position: On the Methodological Pitfalls of Evaluating Base LLMs for Reasoning
di: Chan, Jason, et al.
Pubblicazione: (2025)

It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
di: Li, Yue, et al.
Pubblicazione: (2025)

RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning
di: Chan, Jason, et al.
Pubblicazione: (2024)

Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs
di: Chan, Jason, et al.
Pubblicazione: (2026)

Invariant Learning with Annotation-free Environments
di: Le, Phuong Quynh, et al.
Pubblicazione: (2025)

Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
di: Le, Phuong Quynh, et al.
Pubblicazione: (2024)

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?
di: Lewis-Lim, Samuel, et al.
Pubblicazione: (2025)

Explanation format does not matter; but explanations do -- An Eggsbert study on explaining Bayesian Optimisation tasks
di: Chakraborty, Tanmay, et al.
Pubblicazione: (2025)

Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives
di: Sarumi, Olufunke O., et al.
Pubblicazione: (2025)

The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum
di: Sarumi, Olufunke O., et al.
Pubblicazione: (2025)

Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classification
di: De Santi, Lisa Anita, et al.
Pubblicazione: (2024)

From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks
di: Datta, Ayan, et al.
Pubblicazione: (2026)

Trace and Edit Relation Associations in GPT
di: Li, Jiahang, et al.
Pubblicazione: (2023)

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
di: Kuhn, Lukas, et al.
Pubblicazione: (2025)

Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
di: Zhao, Zhixue, et al.
Pubblicazione: (2024)

Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges
di: Pathak, Shreyasi, et al.
Pubblicazione: (2024)

Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions
di: Nie, Shangrui, et al.
Pubblicazione: (2025)

Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models
di: Li, Yue, et al.
Pubblicazione: (2024)

Learning to Edit: Aligning LLMs with Knowledge Editing
di: Jiang, Yuxin, et al.
Pubblicazione: (2024)