相关论文: GOLD: Generalized Knowledge Distillation via Out-o…

Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs)…

Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by…

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategies for low-resource language settings is lacking. While…

Conventional knowledge distillation, designed for model compression, fails on long-tailed distributions because the teacher model tends to be biased toward head classes and provides limited supervision for tail classes. We propose…

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…

Compared to standard language model (LM) pretraining (i.e., from scratch), Knowledge Distillation (KD) entails an additional forward pass through a teacher model that is typically substantially larger than the target student model. As such,…

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…

Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it…

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

Knowledge distillation typically transfers knowledge from a teacher model to a student model by minimizing differences between their output distributions. However, existing distillation approaches largely focus on mimicking absolute…

One of the most reliable ways to create deployable models for specialized tasks is to obtain an adequate amount of high-quality task-specific data. However, for specialized tasks, often such datasets do not exist. Existing methods address…

Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck,…

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher…

Diffusion Models (DMs), also referred to as score-based diffusion models, utilize neural networks to specify score functions. Unlike most other probabilistic models, DMs directly model the score functions, which makes them more flexible to…

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a…

Graph Neural Networks (GNNs) have shown exceptional performance in the task of link prediction. Despite their effectiveness, the high latency brought by non-trivial neighborhood data dependency limits GNNs in practical deployments.…