Arnav Chavan


2024

pdf bib
Surgical Feature-Space Decomposition of LLMs: Why, When and How?
Arnav Chavan | Nahush Lele | Deepak Gupta
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Low-rank approximations, of the weight and feature space can enhance the performance of deep learning models, whether in terms of improving generalization or reducing the latency of inference. However, there is no clear consensus yet on how, when and why these approximations are helpful for large language models (LLMs). In this work, we empirically study the efficacy of weight and feature space decomposition in transformer-based LLMs. We demonstrate that surgical decomposition not only provides critical insights into the trade-off between compression and language modelling performance, but also sometimes enhances commonsense reasoning performance of LLMs. Our empirical analysis identifies specific network segments that intrinsically exhibit a low-rank structure. Furthermore, we extend our investigation to the implications of low-rank approximations on model bias. Overall, our findings offer a novel perspective on optimizing LLMs, presenting the low-rank approximation not only as a tool for performance enhancements, but also as a means to potentially rectify biases within these models.

2023

pdf bib
A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models
Krithika Ramesh | Arnav Chavan | Shrey Pandit | Sunayana Sitaram
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Compression techniques for deep learning have become increasingly popular, particularly in settings where latency and memory constraints are imposed. Several methods, such as pruning, distillation, and quantization, have been adopted for compressing models, each providing distinct advantages. However, existing literature demonstrates that compressing deep learning models could affect their fairness. Our analysis involves a comprehensive evaluation of pruned, distilled, and quantized language models, which we benchmark across a range of intrinsic and extrinsic metrics for measuring bias in text classification. We also investigate the impact of using multilingual models and evaluation measures. Our findings highlight the significance of considering both the pre-trained model and the chosen compression strategy in developing equitable language technologies. The results also indicate that compression strategies can have an adverse effect on fairness measures.