paper-with-me

Papers

A Primer on the Inner Workings of Transformer-based Language Models

2024-04-30 · Javier Ferrando, Gabriele Sarti, Arianna Bisazza, Marta R. Costa-jussà

The rapid progress of research aimed at interpreting the inner workings of advanced language models has highlighted a need for contextualizing the insights gained from years of work in this area. This primer provides a concise technical introduction to the current techniques used to interpret the inner workings of Transformer-based language models, focusing on the generative decoder-only architecture. We conclude by presenting a comprehensive overview of the known internal mechanisms implemented by these models, uncovering connections across popular approaches and active research directions in this area.

📄 PDF Abstract BibTeX arXiv:2405.00208

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Similar Papers 제목 키워드 기반

A mathematical perspective on Transformers

2023-12-17 · Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, Philippe Rigollet

Transformers play a central role in the inner workings of large language models. We develop a mathematical framework for analyzing Transformers based on their interpretation as interacting particle systems, which reveals…

Primer: Searching for Efficient Transformers for Language Modeling

2021-09-17 · David R. So, Wojciech Mańke, Hanxiao Liu, Zihang Dai 외

Large Transformer models have been central to recent advances in natural language processing. The training and inference costs of these models, however, have grown rapidly and become prohibitively expensive. Here we aim …

Language ModelingLanguage Modelling

Searching for Efficient Transformers for Language Modeling

2021-12-01 · NeurIPS 2021 12 · David So, Wojciech Mańke, Hanxiao Liu, Zihang Dai 외

Large Transformer models have been central to recent advances in natural language processing. The training and inference costs of these models, however, have grown rapidly and become prohibitively expensive. Here we aim …

Language ModelingLanguage Modelling

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models

2026-05-30 · Ravil Mussabayev, Rustam Mussabayev arxiv

This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations within Multimodal Large Language Models (MLLMs). Our system evaluates the linearity, intrinsic dimension, and anisotrop…

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

2026-06-04 · Tang Li, Yanlin Chen, Mengmeng Ma, Xi Peng arxiv

Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment. Sparse autoencoders (SAEs) provide a promising lens …