paper-with-me

홈 › Papers

Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors

2025-02-27 · Kohei Tsuji, Tatsuya Hiraoka, Yuchang Cheng, Eiji Aramaki, Tomoya Iwakura

This paper investigates how LLMs encode inputs with typos. We hypothesize that specific neurons and attention heads recognize typos and fix them internally using local and global contexts. We introduce a method to identify typo neurons and typo heads that work actively when inputs contain typos. Our experimental results suggest the following: 1) LLMs can fix typos with local contexts when the typo neurons in either the early or late layers are activated, even if those in the other are not. 2) Typo neurons in the middle layers are responsible for the core of typo-fixing with global contexts. 3) Typo heads fix typos by widely considering the context not focusing on specific tokens. 4) Typo neurons and typo heads work not only for typo-fixing but also for understanding general contexts.

📄 PDF Abstract BibTeX arXiv:2502.19669

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions

2024-02-23 · Clement Neo, Shay B. Cohen, Fazl Barez

Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have b…

Text Generation

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning

2025-07-10 · Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui arxiv

This paper investigates the relationship between large language models' (LLMs) ability to recognize repetitive input patterns and their performance on in-context learning (ICL). In contrast to prior work that has primari…

Reasoning Robustness of LLMs to Adversarial Typographical Errors

2024-11-08 · Esther Gan, Yiran Zhao, Liying Cheng, Yancan Mao 외

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustnes…

GSM8KMMLU

Decomposing Attention To Find Context-Sensitive Neurons

2025-10-01 · Alex Gibson arxiv

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stab…

DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models

2023-10-03 · Albert Garde, Esben Kran, Fazl Barez

As large language models (LLMs) become more capable, there is an urgent need for interpretable and transparent tools. Current methods are difficult to implement, and accessible tools to analyze model internals are lackin…