---
title: "TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00631v1"
permalink: "https://feed.astralor.com/items/itm_ea500a32637e3fca457df4f5"
published: "2026-10-31T04:55:14.000Z"
score: 57
channel: "tech"
tags: ["LLM","TopoQuant","Topological Framework","Characterize Behavioral Shifts","Quantized Large Language","Models Post-training","PTQ","LLMs"]
---

# TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models

## At a glance

Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accu…

## Key points

- Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accu…
- We present TopoQuant, a topological framework that uses topological data analysis (TDA) to quantify structural drift in self-attention weights and relate it to behavioral changes in quantized LLMs.
- Across four LLM families and multiple quantization levels, we show that topological drift remains stable at moderate compression levels but increases sharply below 4 bit precision, closely tracking declines in attention…

## Full text

Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accuracy and per plexity. We present TopoQuant, a topological framework that uses topological data analysis (TDA) to quantify structural drift in self-attention weights and relate it to behavioral changes in quantized LLMs. Across four LLM families and multiple quantization levels, we show that topological drift remains stable at moderate compression levels but increases sharply below 4 bit precision, closely tracking declines in attention agreement. Our results reveal a strong relationship between topological drift and attention agreement, indicating that structural changes in model parameters closely reflect behavioral degradation under quantization. We further demonstrate that topological features can accurately predict attention consistency using lightweight machine learning models, achieving R2 scores of up to 0.85. Predicting attention agreement enables efficient assessment of be havioral consistency in quantized LLMs, allowing quantization induced degradation to be detected without running expensive downstream tasks. The results indicate that topological drift pro vides an efficient early-warning signal for quantization-induced degradation and can help identify safe compression limits without extensive downstream evaluation.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_ea500a32637e3fca457df4f5