Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2310.00867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910333376921600 |
|---|---|
| author | Hoang, Duc N. M Cho, Minsik Merth, Thomas Rastegari, Mohammad Wang, Zhangyang |
| author_facet | Hoang, Duc N. M Cho, Minsik Merth, Thomas Rastegari, Mohammad Wang, Zhangyang |
| contents | Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs' inherent knowledge and the possible remedies. We start by proposing two conjectures on the nature of the damage: one is certain knowledge being forgotten (or erased) after LLM compression, hence necessitating the compressed model to (re)learn from data with additional parameters; the other presumes that knowledge is internally displaced and hence one requires merely "inference re-direction" with input-side augmentation such as prompting, to recover the knowledge-related performance. Extensive experiments are then designed to (in)validate the two conjectures. We observe the promise of prompting in comparison to model tuning; we further unlock prompting's potential by introducing a variant called Inference-time Dynamic Prompting (IDP), that can effectively increase prompt diversity without incurring any inference overhead. Our experiments consistently suggest that compared to the classical re-training alternatives such as LoRA, prompting with IDP leads to better or comparable post-compression performance recovery, while saving the extra parameter size by 21x and reducing inference latency by 60%. Our experiments hence strongly endorse the conjecture of "knowledge displaced" over "knowledge forgotten", and shed light on a new efficient mechanism to restore compressed LLM performance. We additionally visualize and analyze the different attention and activation patterns between prompted and re-trained models, demonstrating they achieve performance recovery in two different regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_00867 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications Hoang, Duc N. M Cho, Minsik Merth, Thomas Rastegari, Mohammad Wang, Zhangyang Computation and Language Artificial Intelligence Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs' inherent knowledge and the possible remedies. We start by proposing two conjectures on the nature of the damage: one is certain knowledge being forgotten (or erased) after LLM compression, hence necessitating the compressed model to (re)learn from data with additional parameters; the other presumes that knowledge is internally displaced and hence one requires merely "inference re-direction" with input-side augmentation such as prompting, to recover the knowledge-related performance. Extensive experiments are then designed to (in)validate the two conjectures. We observe the promise of prompting in comparison to model tuning; we further unlock prompting's potential by introducing a variant called Inference-time Dynamic Prompting (IDP), that can effectively increase prompt diversity without incurring any inference overhead. Our experiments consistently suggest that compared to the classical re-training alternatives such as LoRA, prompting with IDP leads to better or comparable post-compression performance recovery, while saving the extra parameter size by 21x and reducing inference latency by 60%. Our experiments hence strongly endorse the conjecture of "knowledge displaced" over "knowledge forgotten", and shed light on a new efficient mechanism to restore compressed LLM performance. We additionally visualize and analyze the different attention and activation patterns between prompted and re-trained models, demonstrating they achieve performance recovery in two different regimes. |
| title | Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2310.00867 |