Cover Image

BlockCert: Certified Blockwise Extraction of Transformer Mechanisms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Andric, Sandro
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Brain-Grounded Axes for Reading and Steering LLM States
by: Andric, Sandro
Published: (2025)

Do Large Language Models Walk Their Talk? Measuring the Gap Between Implicit Associations, Self-Report, and Behavioral Altruism
by: Andric, Sandro
Published: (2025)

Exploring and Improving Drafts in Blockwise Parallel Decoding
by: Kim, Taehyeon, et al.
Published: (2024)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
by: Pavlenko, Kirill, et al.
Published: (2026)

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
by: Xu, Peng, et al.
Published: (2024)

When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation
by: Andric, Sandro
Published: (2026)

Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
by: Qiao, Ting, et al.
Published: (2025)

Transformer Block Coupling and its Correlation with Generalization in LLMs
by: Aubry, Murdock, et al.
Published: (2024)

Certifying Knowledge Comprehension in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Block Transformer: Global-to-Local Language Modeling for Fast Inference
by: Ho, Namgyu, et al.
Published: (2024)

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
by: Lorenz, Tobias, et al.
Published: (2024)

CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction
by: Qiao, Ting, et al.
Published: (2025)

ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction
by: Naglik, Iwo, et al.
Published: (2024)

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
by: Shopkhoev, Dmitriy, et al.
Published: (2025)

Certified Robustness Under Bounded Levenshtein Distance
by: Rocamora, Elias Abad, et al.
Published: (2025)

Automata Extraction from Transformers
by: Zhang, Yihao, et al.
Published: (2024)

Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs
by: Wang, Ganghua, et al.
Published: (2025)

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models
by: Yuan, Fei, et al.
Published: (2024)

The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems
by: Sinha, Debu
Published: (2025)

Block-Attention for Efficient Prefilling
by: Ma, Dongyang, et al.
Published: (2024)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
by: Lv, Ang, et al.
Published: (2024)

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

Certifying LLM Safety against Adversarial Prompting
by: Kumar, Aounon, et al.
Published: (2023)

MoBA: Mixture of Block Attention for Long-Context LLMs
by: Lu, Enzhe, et al.
Published: (2025)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
by: Guo, Song, et al.
Published: (2024)

NLP Verification: Towards a General Methodology for Certifying Robustness
by: Casadio, Marco, et al.
Published: (2024)

Interactions Across Blocks in Post-Training Quantization of Large Language Models
by: Shabanovi, Khasmamad, et al.
Published: (2024)

Distantly-Supervised Joint Extraction with Noise-Robust Learning
by: Li, Yufei, et al.
Published: (2023)

LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
by: Nagar, Aishik, et al.
Published: (2024)

GLiREL -- Generalist Model for Zero-Shot Relation Extraction
by: Boylan, Jack, et al.
Published: (2025)

LMDX: Language Model-based Document Information Extraction and Localization
by: Perot, Vincent, et al.
Published: (2023)

An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction
by: Zaratiana, Urchade, et al.
Published: (2024)

Student sentiment Analysis Using Classification With Feature Extraction Techniques
by: Tamrakar, Latika, et al.
Published: (2021)

Distilling Multi-Scale Knowledge for Event Temporal Relation Extraction
by: Yao, Hao-Ren, et al.
Published: (2022)

Graphical Reasoning: LLM-based Semi-Open Relation Extraction
by: Tao, Yicheng, et al.
Published: (2024)

Comparing Feature Importance and Rule Extraction for Interpretability on Text Data
by: Lopardo, Gianluigi, et al.
Published: (2022)

Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content
by: Rizvi, F. A., et al.
Published: (2025)

GPT-3 Powered Information Extraction for Building Robust Knowledge Bases
by: Choudhury, Ritabrata Roy, et al.
Published: (2024)

KnowCoder-X: Boosting Multilingual Information Extraction via Code
by: Zuo, Yuxin, et al.
Published: (2024)

Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis
by: Tan, Zhiyin, et al.
Published: (2026)