Related papers: X-Token: Projection-Guided Cross-Tokenizer Knowled…

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging…

Deploying large language models (LLMs) of several billion parameters can be impractical in most industrial use cases due to constraints such as cost, latency limitations, and hardware accessibility. Knowledge distillation (KD) offers a…

Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem. Existing approaches rely on heuristic strategies to align…

Large language models (LLMs) offer impressive performance but are impractical for resource-constrained deployment due to high latency and energy consumption. Knowledge distillation (KD) addresses this by transferring knowledge from a large…

Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be used, enabling the use of any teacher model trained on a…

Knowledge distillation (KD) has become a prevalent technique for compressing large language models (LLMs). Existing KD methods are constrained by the need for identical tokenizers (i.e., vocabularies) between teacher and student models,…

Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the…

Large Language Models (LLMs) achieve state-of-the-art performance across various NLP tasks but face deployment challenges due to high computational costs and memory constraints. Knowledge distillation (KD) is a promising solution,…

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…

Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on tokens sampled from the teacher (hard labels) or the teacher's full next-token…

Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common issue named…

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its…

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we…

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…

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key challenges: (1) information loss from hard pruning, (2)…

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…