| Challenge: | Existing work quantifying energy costs and associated carbon emissions has focused on pretraining and fine-tuning. |
| Approach: | They perform an empirical study to quantify the energy requirements of language model fine-tuning in the context of pretraining and inference. |
| Outcome: | The proposed model fine-tuning energy and carbon footprints are compared with pre-training and inference energy requirements and outline recommendations for NLP researchers and practitioners. |
Similar Papers
Energy and Policy Considerations for Deep Learning in NLP (P19-1)
Copied to clipboard
| Challenge: | Recent advances in hardware and methodology for training neural networks have enabled significant accuracy improvements across many NLP tasks. |
| Approach: | They quantify the approximate financial and environmental costs of training neural network models . they propose actionable recommendations to reduce costs and improve equity in NLP research . |
| Outcome: | The proposed recommendations address the cost and environmental costs of training neural networks for NLP. |
TopicBERT for Energy Efficient Document Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has noted that BERT’s computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. |
| Approach: | They propose to combine topic and language models to optimize the computational cost of fine-tuning for document classification by complementary learning. |
| Outcome: | The proposed model achieves a 1.4x speedup with 40% reduction in CO2 emission while retaining 99.9% performance over 5 datasets. |
Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies show that the energy requirements of current NLP models are growing at a rapid, unsustainable pace. |
| Approach: | They investigate ways to measure energy usage and different hardware settings that can be tuned to reduce energy consumption for training and inference for language models. |
| Outcome: | The proposed techniques can reduce energy consumption for training and inference for language models. |
Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular. |
| Approach: | They compare performance of financial BERT-like models to their fully fine-tuned counterparts by using parameter-efficient tuning methods. |
| Outcome: | The proposed approaches match full fine-tuning performance on common NLP tasks, but are less studied in finance. |
A Closer Look at How Fine-tuning Changes BERT (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained contextualized representations are used to analyze information in NLP . however, how fine-tuning changes the underlying embedding space is less studied . |
| Approach: | They propose to use probing techniques to analyze how fine-tuning changes the embedding space of pre-trained contextualized representations. |
| Outcome: | The proposed model improves classification performance by increasing the distances between examples associated with different labels. |
Modular and Parameter-Efficient Fine-Tuning for NLP Models (2022.emnlp-tutorials)
Copied to clipboard
| Challenge: | State-of-the-art language models in NLP perform best when fine-tuned even on small datasets. |
| Approach: | They provide an overview of parameter-efficient fine-tuning methods and highlight similarities and differences . they highlight benefits and usage scenarios of a neglected property of parameter efficient models . |
| Outcome: | This paper provides an overview of parameter-efficient fine-tuning methods . it highlights similarities and differences by presenting them in a unified view . |
On the Nature of BERT: Correlating Fine-Tuning and Linguistic Competence (2022.coling-1)
Copied to clipboard
| Challenge: | Several studies on the interpretation of Neural Language Models (NLMs) focus on the linguistic generalization abilities of pre-trained models, but little attention is paid to how the linguistic knowledge of the models changes during fine-tuning. |
| Approach: | They propose to examine whether a wide range of linguistic phenomena are forgotten during fine-tuning and whether it is possible to predict the fine- tuned accuracy solely relying on the assessed linguistic competence. |
| Outcome: | The proposed model can predict the evolution of written language competence of native language learners based on the assessed linguistic competence. |
Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are recognized for their exceptional generative capabilities and versatility across various tasks. |
| Approach: | They conduct a comprehensive benchmarking of LLM inference energy across a wide range of NLP tasks to determine the impact of different models, tasks, prompts, and system-related factors on inference. |
| Outcome: | The proposed model energy benchmarks show that quantization and optimal batch sizes can significantly reduce energy usage. |
On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | linguistic knowledge encoded in pre-trained contextual embeddings is poorly understood . fine-tuning can be used to investigate the representations of pre-train models . |
| Approach: | They propose to investigate fine-tuning of contextualized embedding models through sentence-level probing. |
| Outcome: | The proposed method improves probing accuracy for three pre-trained models. |
Using NLP to quantify the environmental cost and diversity benefits of in-person NLP conferences (2022.findings-acl)
Copied to clipboard
| Challenge: | Figure 1 shows the increase in travel to the ACL annual meeting over the past 40 years . |
| Approach: | They analyse the carbon cost associated with journeys made by researchers attending in-person NLP conferences by text-mining publications from the ACL anthology . |
| Outcome: | The proposed model compares the carbon cost associated with travel to in-person conferences to previously known values for training large models. |