Metaphors are commonly found in advertising and internet memes. However, the free form of internet memes often leads to a lack of high-quality textual data. Metaphor detection demands a deep interpretation of both textual and visual elements, requiring extensive common-sense knowledge, which poses a challenge to language models. To address these challenges, we propose a compact framework called C4MMD, which utilizes a Chain-of-Thought(CoT) method for Multi-modal Metaphor Detection. Specifically, our approach designs a three-step process inspired by CoT that extracts and integrates knowledge from Multi-modal Large Language Models(MLLMs) into smaller ones. We also developed a modality fusion architecture to transform knowledge from large models into metaphor features, supplemented by auxiliary tasks to improve model performance. Experimental results on the MET-MEME dataset demonstrate that our method not only effectively enhances the metaphor detection capabilities of small models but also outperforms existing models. To our knowledge, this is the first systematic study leveraging MLLMs in metaphor detection tasks. The code for our method is publicly available at https://github.com/xyz189411yt/C4MMD.

Teaching small-scale language models to perform math reasoning is a valuable yet challenging task. Besides obtaining labeled data from human experts, one of the most common ways to collect high-quality data is by sampling from a larger and more powerful language model. Although previous works have demonstrated the effectiveness of this method, such a knowledge distillation paradigm can be costly and unstable, especially considering that many large language models, such as GPT-4, are closed-sourced, proprietary, and their behaviors are unpredictable. In this work, to avoid relying on outputs from large models, we demonstrate that the reasoning abilities of small-scale language models can be enhanced through self-training, which involves training models with their own outputs. We also show that the vanilla self-training can be further augmented by an alignment algorithm, direct preference optimization (DPO). We empirically found that models trained with the DPO objective are capable of making better generations that largely benefit multi-turn self-training. The experiments show our models outperform the state-of-the-art models with comparable sizes on a series of downstream math reasoning tasks with minimal resource requirements.

Employing pre-trained generation models for cross-domain aspect-based sentiment classification has recently led to large improvements. However, they ignore the importance of syntactic structures, which have shown appealing effectiveness in classification based models. Different from previous studies, efficiently encoding the syntactic structure in generation model is challenging because such models are pretrained on natural language, and modeling structured data may lead to catastrophic forgetting of distributional knowledge. In this study, we propose a novel structure-aware generation model to tackle this challenge. In particular, a prompt-driven strategy is designed to bridge the gap between different domains, by capturing implicit syntactic information from the input and output sides. Furthermore, the syntactic structure is explicitly encoded into the structure-aware generation model, which can effectively learn domain-irrelevant features based on syntactic pivot features. Empirical results demonstrate the effectiveness of the proposed structure-aware generation model over several strong baselines. The results also indicate the proposed model is capable of leveraging the input syntactic structure into the generation model.

Previous studies on cross-domain sentiment classification depend on the pivot features or utilize the target data for representation learning, which ignore the semantic relevance between different domains. To this end, we exploit Abstract Meaning Representation (AMR) to help with cross-domain sentiment classification. Compared with the textual input, AMR reduces data sparsity and explicitly provides core semantic knowledge and correlations between different domains. In particular, we develop an algorithm to construct a sentiment-driven semantic graph from sentence-level AMRs. We further design two strategies to linearize the semantic graph and propose a text-graph interaction model to fuse the text and semantic graph representations for cross-domain sentiment classification. Empirical studies show the effectiveness of our proposed model over several strong baselines. The results also indicate the importance of the proposed sentiment-driven semantic graph for cross-domain sentiment classification.