12 papers
Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
Haolin Yang, Hakaze Cho, Kaize Ding +1
Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations a…
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
Haolin Yang, Hakaze Cho, Naoya Inoue
We investigate the mechanistic underpinnings of in-context learning (ICL) in large language models by reconciling two dominant perspectives: the component-level analysis of attenti…
Binary Autoencoder for Mechanistic Interpretability of Large Language Models
Hakaze Cho, Haolin Yang, Yanshu Li +2
Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoenco…
Mechanism of Task-oriented Information Removal in In-context Learning
Hakaze Cho, Haolin Yang, Gouki Minegishi +1
In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate th…
Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
Haolin Yang, Hakaze Cho, Yiqiao Zhong +1
The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either speci…
Mechanistic Fine-tuning for In-context Learning
Hakaze Cho, Peng Luo, Mariko Kato +2
In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style dat…