paper-with-me

홈 › Papers

Probing Information Distribution in Transformer Architectures through Entropy Analysis

2025-07-21 · Amedeo Buonanno, Alessandro Rivetti, Francesco A. N. Palmieri, Giovanni Di Gennaro, Gianmarco Romano arxiv

This work explores entropy analysis as a tool for probing information distribution within Transformer-based architectures. By quantifying token-level uncertainty and examining entropy patterns across different stages of processing, we aim to investigate how information is managed and transformed within these models. As a case study, we apply the methodology to a GPT-based large language model, illustrating its potential to reveal insights into model behavior and internal representations. This approach may offer insights into model behavior and contribute to the development of interpretability and evaluation frameworks for transformer-based models

📄 PDF Abstract BibTeX arXiv:2507.15347

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Domain-Informed Probing of wav2vec 2.0 Embeddings for Phonetic Features

2022-07-01 · NAACL (SIGMORPHON) 2022 7 · Patrick Cormac English, John D. Kelleher, Julie Carson-Berndsen

In recent years large transformer model architectures have become available which provide a novel means of generating high-quality vector representations of speech audio. These transformers make use of an attention mecha…

Speaker Verificationspeech-recognitionSpeech Recognition

Layer by layer, module by module: Choose both for optimal OOD probing of ViT

2026-03-05 · Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel, Romain Tavenard 외 arxiv

Recent studies have observed that intermediate layers of foundation models often yield more discriminative representations than the final layer. While initially attributed to autoregressive pretraining, this phenomenon h…

Image Classification

SSA: Improving Performance With a Better Scoring Function

2025-08-20 · Omar Naim, Swarnadeep Bhar, Jérôme Bolte, Nicholas Asher arxiv

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the att…

Understanding Transformer Memorization Recall Through Idioms

2022-10-07 · Adi Haviv, Ido Cohen, Jacob Gidron, Roei Schuster 외

To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does…

Memorization

GPT-2 Through the Lens of Vector Symbolic Architectures

2024-12-10 · Johannes Knittel, Tushaar Gangavarapu, Hendrik Strobelt, Hanspeter Pfister

Understanding the general priniciples behind transformer models remains a complex endeavor. Experiments with probing and disentangling features using sparse autoencoders (SAE) suggest that these models might manage linea…

Decoder