相关论文: Weighted KL-Divergence for Document Ranking Model …

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Two step document ranking, where the initial retrieval is done by a classical information retrieval method, followed by neural re-ranking model, is the new standard. The best performance is achieved by using transformer-based models as…

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.…

Although BERT-based ranking models have been commonly used in commercial search engines, they are usually time-consuming for online ranking tasks. Knowledge distillation, which aims at learning a smaller model with comparable performance to…

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to…

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

In many learning problems, the training and testing data follow different distributions and a particularly common situation is the \textit{covariate shift}. To correct for sampling biases, most approaches, including the popular kernel mean…

Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings additional complications, which prevent wider adoption. In this…

Recent research has reported a performance degradation in self-supervised contrastive learning for specially designed efficient networks, such as MobileNet and EfficientNet. A common practice to address this problem is to introduce a…

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this…

Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several…

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…

Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e.g., reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL…

Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous…

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger…

Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation…

We address the computational cost of constructing a model map, which embeds diverse language models into a common space for comparison via KL divergence. The map relies on log-likelihoods over a large text set, making the cost proportional…

The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model).…