When Quantization Affects Confidence of Large Language Models?

Anonymous

TL;DR: Impact of compression of LLM on three aspects : (i) decrease in confidence regarding true labels (ii) impact on confidence across different scales (iii) explanation for quantization loss based on confidence levels

Abstract:

Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation.
Although quantized weights offer storage efficiency and allow for faster inference, existing works have indicated that quantization might compromise performance and exacerbate biases in LLMs.
This study investigates the confidence and calibration of quantized models, considering factors such as language model type and scale as contributors to quantization loss.
Firstly, we reveal that quantization leads to a decrease in confidence regarding true labels, with varying impacts observed among different language models. Secondly, we observe fluctuations in the impact on confidence across different scales. Finally, we propose an explanation for quantization loss based on confidence levels, indicating that quantization disproportionately affects samples where the full model exhibited low confidence levels in the first place.

Paper Type: short

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability

Languages Studied: English