层级频率标记探针（HFTP）：一种统一方法用于探究大型语言模型与人类大脑中的句法结构表征

Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

October 15, 2025

作者: Jingmin An, Yilong Song, Ruolin Yang, Nai Ding, Lingxi Lu, Yuxuan Wang, Wei Wang, Chu Zhuang, Qian Wang, Fang Fang

cs.AI

摘要

大型語言模型（LLMs）展現出與人類相當甚至更優越的語言能力，能有效模擬句法結構，然而負責這些能力的具體計算模組仍不明確。一個關鍵問題是，LLM的行為能力是否源自與人腦相似的機制。為探討這些問題，我們引入了層次頻率標記探針（HFTP），這是一種利用頻域分析來識別LLM中負責句法結構的神經元層面組件（例如，個別多層感知器（MLP）神經元）及皮質區域（通過顱內記錄）的工具。我們的結果顯示，如GPT-2、Gemma、Gemma 2、Llama 2、Llama 3.1及GLM-4等模型在處理句法時使用相似的層次，而人腦則依賴不同的皮質區域來處理不同層次的句法。表徵相似性分析揭示，LLM的表徵與大腦左半球（主導語言處理）之間存在更強的對應關係。值得注意的是，升級後的模型呈現出不同的趨勢：Gemma 2比Gemma更接近大腦，而Llama 3.1與大腦的對應程度則低於Llama 2。這些發現為LLM行為改進的可解釋性提供了新的見解，並引發了這些進步是否由類人機制或非類人機制驅動的疑問，同時確立了HFTP作為連接計算語言學與認知神經科學的重要工具。本項目可於https://github.com/LilTiger/HFTP獲取。

English

Large Language Models (LLMs) demonstrate human-level or even superior language abilities, effectively modeling syntactic structures, yet the specific computational modules responsible remain unclear. A key question is whether LLM behavioral capabilities stem from mechanisms akin to those in the human brain. To address these questions, we introduce the Hierarchical Frequency Tagging Probe (HFTP), a tool that utilizes frequency-domain analysis to identify neuron-wise components of LLMs (e.g., individual Multilayer Perceptron (MLP) neurons) and cortical regions (via intracranial recordings) encoding syntactic structures. Our results show that models such as GPT-2, Gemma, Gemma 2, Llama 2, Llama 3.1, and GLM-4 process syntax in analogous layers, while the human brain relies on distinct cortical regions for different syntactic levels. Representational similarity analysis reveals a stronger alignment between LLM representations and the left hemisphere of the brain (dominant in language processing). Notably, upgraded models exhibit divergent trends: Gemma 2 shows greater brain similarity than Gemma, while Llama 3.1 shows less alignment with the brain compared to Llama 2. These findings offer new insights into the interpretability of LLM behavioral improvements, raising questions about whether these advancements are driven by human-like or non-human-like mechanisms, and establish HFTP as a valuable tool bridging computational linguistics and cognitive neuroscience. This project is available at https://github.com/LilTiger/HFTP.