Cover Image

As easy as PIE: understanding when pruning causes language models to disagree

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tropeano, Pietro, Maistro, Maria, Ruotsalo, Tuukka, Lioma, Christina
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Stairway to Fairness: Connecting Group and Individual Fairness
by: Rampisela, Theresia Veronika, et al.
Published: (2025)

The Quest for Reliable Metrics of Responsible AI
by: Rampisela, Theresia Veronika, et al.
Published: (2025)

Measuring Individual User Fairness with User Similarity and Effectiveness Disparity
by: Rampisela, Theresia Veronika, et al.
Published: (2026)

Are Representation Disentanglement and Interpretability Linked in Recommendation Models? A Critical Review and Reproducibility Study
by: Dervishaj, Ervin, et al.
Published: (2025)

Post-Training Denoising of User Profiles with LLMs in Collaborative Filtering Recommendation
by: Dervishaj, Ervin, et al.
Published: (2026)

Joint Evaluation of Fairness and Relevance in Recommender Systems with Pareto Frontier
by: Rampisela, Theresia Veronika, et al.
Published: (2025)

Can We Trust Recommender System Fairness Evaluation? The Role of Fairness and Relevance
by: Rampisela, Theresia Veronika, et al.
Published: (2024)

Evaluation Measures of Individual Item Fairness for Recommender Systems: A Critical Study
by: Rampisela, Theresia Veronika, et al.
Published: (2023)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
by: Adarsh, Shivam, et al.
Published: (2026)

BrainLLM: Generative Language Decoding from Brain Recordings
by: Ye, Ziyi, et al.
Published: (2023)

Query Augmentation by Decoding Semantics from Brain Signals
by: Ye, Ziyi, et al.
Published: (2024)

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
by: Edin, Joakim, et al.
Published: (2025)

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
by: Marjanović, Sara Vera, et al.
Published: (2024)

Joint Extraction and Classification of Danish Competences for Job Matching
by: Li, Qiuchi, et al.
Published: (2024)

A Reality Check on Context Utilisation for Retrieval-Augmented Generation
by: Hagström, Lovisa, et al.
Published: (2024)

Physiological Data: Challenges for Privacy and Ethics
by: Davis, Keith, et al.
Published: (2024)

Recommending Target Actions Outside Sessions in the Data-poor Insurance Domain
by: Bruun, Simone Borg, et al.
Published: (2024)

Investigating the Impact of Model Instability on Explanations and Uncertainty
by: Marjanović, Sara Vera, et al.
Published: (2024)

What does it mean to understand language?
by: Casto, Colton, et al.
Published: (2025)

GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models
by: Jassim, Serwan, et al.
Published: (2023)

An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records
by: Edin, Joakim, et al.
Published: (2024)

Towards understanding evolution of science through language model series
by: Dong, Junjie, et al.
Published: (2024)

Lost without translation -- Can transformer (language models) understand mood states?
by: Shivaprakash, Prakrithi, et al.
Published: (2025)

Logical forms complement probability in understanding language model (and human) performance
by: Wang, Yixuan, et al.
Published: (2025)

DocLLM: A layout-aware generative language model for multimodal document understanding
by: Wang, Dongsheng, et al.
Published: (2023)

Can large language models understand uncommon meanings of common words?
by: Wu, Jinyang, et al.
Published: (2024)

CMMLU: Measuring massive multitask language understanding in Chinese
by: Li, Haonan, et al.
Published: (2023)

Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability
by: Edin, Joakim, et al.
Published: (2024)

Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
by: Grizou, Jonathan, et al.
Published: (2025)

Enriching language models with graph-based context information to better understand textual data
by: Roethel, Albert, et al.
Published: (2023)

Practical token pruning for foundation models in few-shot conversational virtual assistant systems
by: Qi, Haode, et al.
Published: (2024)

Integrating large language models and active inference to understand eye movements in reading and dyslexia
by: Donnarumma, Francesco, et al.
Published: (2023)

\textsc{CantoNLU}: A benchmark for Cantonese natural language understanding
by: Min, Junghyun, et al.
Published: (2025)

Recursive numeral systems are highly regular and easy to process
by: Prasertsom, Ponrawee, et al.
Published: (2025)

Out-of-distribution generalisation in spoken language understanding
by: Porjazovski, Dejan, et al.
Published: (2024)

CULL-MT: Compression Using Language and Layer pruning for Machine Translation
by: Rostami, Pedram, et al.
Published: (2024)

What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
by: Galke, Lukas, et al.
Published: (2023)

Are LLM-generated plain language summaries truly understandable? A large-scale crowdsourced evaluation
by: Guo, Yue, et al.
Published: (2025)

"What's my model inside of?": Exploring the role of environments for grounded natural language understanding
by: Tamari, Ronen
Published: (2024)

Can large audio language models understand child stuttering speech? speech summarization, and source separation
by: Okocha, Chibuzor, et al.
Published: (2025)