Knowledge distillation (KD) is a widely used approach for BERT compression, where a larger BERT model serves as a teacher to transfer knowledge to a smaller student model.Prior works have found that distilling a larger BERT with superior performance may degrade student's performance than a smaller BERT.In this paper, we investigate the limitations of existing KD methods for larger BERT models.Through Canonical Correlation Analysis, we identify that these methods fail to fully exploit the potential advantages of larger teachers.To address this, we propose an improved distillation approach that effectively enhances knowledge transfer.Comprehensive experiments demonstrate the effectiveness of our method in enabling larger BERT models to distill knowledge more efficiently.

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model’s responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination.To eliminate hallucinations, existing methods manually annotate paired responses with and without hallucinations, and then employ various alignment algorithms to improve the alignment capability between images and text.However, they not only demand considerable computation resources during the finetuning stage but also require expensive human annotation to construct paired data needed by the alignment algorithms.To address these issues, we propose an efficient fine-grained unlearning framework (EFUF), which performs gradient ascent utilizing three tailored losses to eliminate hallucinations without paired data.Extensive experiments show that our method consistently reduces hallucinations while preserving the generation quality with modest computational overhead.Our code and datasets are available at https://github.com/starreeze/efuf.

Multimodal Entity Linking (MEL) is a task that aims to link ambiguous mentions within multimodal contexts to referential entities in a multimodal knowledge base. Recent methods for MEL adopt a common framework: they first interact and fuse the text and image to obtain representations of the mention and entity respectively, and then compute the similarity between them to predict the correct entity. However, these methods still suffer from two limitations: first, as they fuse the features of text and image before matching, they cannot fully exploit the fine-grained alignment relations between the mention and entity. Second, their alignment is static, leading to low performance when dealing with complex and diverse data. To address these issues, we propose a novel framework called Dynamic Relation Interactive Network (DRIN) for MEL tasks. DRIN explicitly models four different types of alignment between a mention and entity and builds a dynamic Graph Convolutional Network (GCN) to dynamically select the corresponding alignment relations for different input samples. Experiments on two datasets show that DRIN outperforms state-of-the-art methods by a large margin, demonstrating the effectiveness of our approach. Our code and datasets are publicly available.

Thanks to the recent breakthroughs in deep learning (DL) methods and ever-increasing computation power, nowadays DL models are being increasingly applied to all kinds of fields. They, along with other software modules, compose complex DL systems such as autonomous driving systems. Unfortunately, fatalities happen to these systems as is reported in real-life situations, e.g., traffic accidents involving autonomous driving vehicles. Further analyses show that this is because DL systems contain defects. To this end, understanding defects in DL systems is critical for preventing such accidents. To help improve the reliability of DL systems, many researchers have devoted efforts to their testing. In this paper, we investigated state-of-the-art methods through in-depth exploration. Firstly, we made a detailed analysis of deep learning system defects. We proposed a defect classification scheme, and summarized the characteristics of defects and their impacts on the system. Secondly, we systematically investigated the detection methods and tools and evaluated their capability in defect detection.

Multimodal Named Entity Recognition (MNER) aims to locate and classify named entities mentioned in a (text, image) pair. However, dominant work independently models the internal matching relations in a pair of image and text, ignoring the external matching relations between different (text, image) pairs inside the dataset, though such relations are crucial for alleviating image noise in MNER task. In this paper, we primarily explore two kinds of external matching relations between different (text, image) pairs, i.e., inter-modal relations and intra-modal relations. On the basis, we propose a Relation-enhanced Graph Convolutional Network (R-GCN) for the MNER task. Specifically, we first construct an inter-modal relation graph and an intra-modal relation graph to gather the image information most relevant to the current text and image from the dataset, respectively. And then, multimodal interaction and fusion are leveraged to predict the NER label sequences. Extensive experimental results show that our model consistently outperforms state-of-the-art works on two public datasets. Our code and datasets are available at https://github.com/1429904852/R-GCN.