Related papers: Bridging Fairness and Environmental Sustainability…
Knowledge Distillation (KD) transfers knowledge from large models to small models and has recently achieved remarkable success. However, the reliability of existing KD methods in real-world applications, especially under distribution shift,…
The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…
Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventional wisdom suggests that fairness criteria promote the…
Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…
With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…
Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g.,…
This paper highlights the significance of natural language processing (NLP) within artificial intelligence, underscoring its pivotal role in comprehending and modeling human language. Recent advancements in NLP, particularly in…
Parallel to the rising debates over sustainable energy and artificial intelligence solutions, the world is currently discussing the ethics of artificial intelligence and its possible negative effects on society and the environment. In these…
The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standard benchmarks has scaled with size, compression techniques…
Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situations, this technique is more of a curse than a blessing.…
This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning…
We present a large-scale empirical study of how choices of configuration parameters affect performance in knowledge distillation (KD). An example of such a KD parameter is the measure of distance between the predictions of the teacher and…
Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD…
Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…
Traditionally, Knowledge Distillation (KD) is used for model compression, often leading to suboptimal performance. In this paper, we evaluate the impact of combining KD loss with alternative pruning techniques, including Low-Rank…
With language models becoming increasingly ubiquitous, it has become essential to address their inequitable treatment of diverse demographic groups and factors. Most research on evaluating and mitigating fairness harms has been concentrated…
Understanding the multifaceted effects of climate change across diverse geographic locations is crucial for timely adaptation and the development of effective mitigation strategies. As the volume of scientific literature on this topic…
This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution holds valuable insights for the student, beyond the…
Knowledge distillation (KD) is a well-known method for compressing neural models. However, works focusing on distilling knowledge from large multilingual neural machine translation (MNMT) models into smaller ones are practically…