English
Related papers

Related papers: Flash Interpretability: Decoding Specialised Featu…

200 papers

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…

Computation and Language · Computer Science 2024-06-12 Haowen Pan , Yixin Cao , Xiaozhi Wang , Xun Yang , Meng Wang

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention…

Computation and Language · Computer Science 2024-04-16 Xintong Wang , Xiaoyu Li , Xingshan Li , Chris Biemann

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…

Computation and Language · Computer Science 2025-05-21 Jiahao Huo , Yibo Yan , Boren Hu , Yutao Yue , Xuming Hu

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Computation and Language · Computer Science 2026-02-05 Yujie Lin , Kunquan Li , Yixuan Liao , Xiaoxin Chen , Jinsong Su

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Computation and Language · Computer Science 2025-06-13 Tatsuya Hiraoka , Kentaro Inui

Advances in Large Language Models (LLMs) have led to remarkable capabilities, yet their inner mechanisms remain largely unknown. To understand these models, we need to unravel the functions of individual neurons and their contribution to…

Machine Learning · Computer Science 2023-06-01 Alex Foote , Neel Nanda , Esben Kran , Ioannis Konstas , Shay Cohen , Fazl Barez

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…

Computation and Language · Computer Science 2023-10-26 Mansi Sakarvadia , Arham Khan , Aswathy Ajith , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Artificial Intelligence · Computer Science 2026-02-03 Jian-Qiao Zhu , Hanbo Xie , Dilip Arumugam , Robert C. Wilson , Thomas L. Griffiths

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

Hardware Architecture · Computer Science 2026-02-10 Xiaoyu Ma , David Patterson

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Computation and Language · Computer Science 2025-06-03 Frederick Riemenschneider , Anette Frank

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

Computation and Language · Computer Science 2025-11-27 Yixiu Zhao , Xiaozhi Wang , Zijun Yao , Lei Hou , Juanzi Li

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…

Computation and Language · Computer Science 2024-05-31 Ernesto Quevedo , Jorge Yero , Rachel Koerner , Pablo Rivas , Tomas Cerny

Decoding non-invasive brain recordings is pivotal for advancing our understanding of human cognition but faces challenges due to individual differences and complex neural signal representations. Traditional methods often require customized…

Neural and Evolutionary Computing · Computer Science 2024-10-15 Guobin Shen , Dongcheng Zhao , Xiang He , Linghao Feng , Yiting Dong , Jihang Wang , Qian Zhang , Yi Zeng

In large language models (LLMs), certain \emph{neurons} can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combination of \emph{relations} and \emph{entities}, it remains…

Large language models (LLMs) not only exhibit human-like performance but also share computational principles with the brain's language processing mechanisms. While prior research has focused on mapping LLMs' internal representations to…

Computation and Language · Computer Science 2025-04-07 Maryam Rahimi , Yadollah Yaghoobzadeh , Mohammad Reza Daliri

We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing…

Computation and Language · Computer Science 2024-02-02 Felipe Urrutia , Cristian Buc , Valentin Barriere