| Total: 57
This work presents a dynamic vocabulary adaptation strategy, MEDVOC, for fine-tuning pre-trained language models (PLMs) like BertSumAbs, BART, and PEGASUS for improved medical text summarization. In contrast to existing domain adaptation approaches in summarization, MEDVOC treats vocabulary as an optimizable parameter and optimizes the PLM vocabulary based on fragment score conditioned only on the downstream task's reference summaries. Unlike previous works on vocabulary adaptation (limited only to classification tasks), optimizing vocabulary based on summarization tasks requires an extremely costly intermediate fine-tuning step on large summarization datasets. To that end, our novel fragment score-based hyperparameter search very significantly reduces this fine-tuning time --- from 450 days to less than 2 days on average. Furthermore, while previous works on vocabulary adaptation are often primarily tied to single PLMs, MEDVOC is designed to be deployable across multiple PLMs (with varying model vocabulary sizes, pre-training objectives, and model sizes) --- bridging the limited vocabulary overlap between the biomedical literature domain and PLMs. MEDVOC outperforms baselines by 15.74% in terms of Rouge-L in zero-shot setting and shows gains of 17.29% in high Out-Of-Vocabulary (OOV) concentrations. Our human evaluation shows MEDVOC generates more faithful medical summaries (88% compared to 59% in baselines).
Memes, initially created for humor and social commentary, have transformed into platforms for offensive online content. Detecting such content is crucial; however, existing deep learning-based meme offensiveness classifiers lack transparency, functioning as opaque black-box systems. While Integrated Gradient and similar input-attribution interpretability methods exist, they often yield inadequate and irrelevant keywords. To bridge this gap, we introduce SEMANTIFY, a novel system featuring a theoretically grounded multi-step filtering process. SEMANTIFY extracts meaningful "tokens" from a predefined vocabulary, generating a pertinent and comprehensive set of interpretable keywords. These extracted keywords reveal the model's awareness of hidden meanings in memes, enhancing transparency. Evaluation of SEMANTIFY using interpretability metrics, including 'leakage-adjusted simulatability,' demonstrates its superiority over various baselines by up to 2.5 points. Human evaluation of 'relatedness' and 'exhaustiveness' of extracted keywords further validates its effectiveness. Additionally, a qualitative analysis of extracted keywords serves as a case study, unveiling model error cases and their reasons. SEMANTIFY contributes to the advancement of more interpretable multimodal systems for meme offensiveness detection, fostering trust for real-world applications.
This paper moves the first step towards automating the composition of Answer Set Programming (ASP) specifications. In particular, the following contributions are provided: (i) A dataset focused on graph-related problem specifications, designed to develop and assess tools for ASP automatic coding; (ii) A two-step architecture, implemented in the NL2ASP tool, for generating ASP programs from natural language specifications. NL2ASP uses neural machine translation to transform natural language into Controlled Natural Language (CNL) statements. Subsequently, CNL statements are converted into ASP code using the CNL2ASP tool. An experimental analysis confirms the viability of the approach.
In this work, we propose a novel tree-based explanation technique, PEACH (Pretrained-embedding Explanation Across Contextual and Hierarchical Structure), that can explain how text-based documents are classified by using any pretrained contextual embeddings in a tree-based human-interpretable manner. Note that PEACH can adopt any contextual embeddings of the PLMs as a training input for the decision tree. Using the proposed PEACH, we perform a comprehensive analysis of several contextual embeddings on nine different NLP text classification benchmarks. This analysis demonstrates the flexibility of the model by appling several PLM contextual embeddings, its attribute selections, scaling, and clustering methods. Furthermore, we show the utility of explanations by visualising the feature selection and important trend of text classification via human-interpretable word-cloud-based trees, which clearly identify model mistakes and assist in dataset debugging. Besides interpretability, PEACH outperforms or is similar to those from pretrained models. Code and Appendix are in https://github.com/adlnlp/peach.
Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications. The accurate identification of hallucinations in texts generated by LLMs, especially in complex inferential scenarios, is a relatively unexplored area. To address this gap, we present FactCHD, a dedicated benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. A distinctive element of FactCHD is its integration of fact-based evidence chains, significantly enhancing the depth of evaluating the detectors' explanations. Experiments on different LLMs expose the shortcomings of current approaches in detecting factual errors accurately. Furthermore, we introduce TRUTH-TRIANGULATOR which synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2, aiming to yield more credible detection through the amalgamation of predictive results and evidence.
Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting—loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain. We further introduce the MSPT framework, designed to surmount the shortcomings of existing MKGC approaches during multimedia data processing. MSPT harmonizes the retention of learned knowledge (stability) and the integration of new data (plasticity), outperforming current continual learning and multimodal methods. Our results confirm MSPT's superior performance in evolving knowledge environments, showcasing its capacity to navigate the balance between stability and plasticity.
End-to-end spoken language understanding (SLU) aims to directly capture the comprehensive semantics from the given spoken utterance without generating any transcript. Since the transcripts might not always be available, Textless SLU is attracting increasing attention, which could eliminate the need for transcripts but often does not perform as well as SLU models trained with transcripts. In this paper, we focus on the scenarios where the transcripts are not available and propose a framework GMA-SLU to generate more audios according to the labels. In order to alleviate the modality gap between text and audio, two language models are developed and discrete tokens are utilized as a bridge, where the first language model utilizes labels to generate semantic tokens and the second language model adopts these obtained semantic tokens and the acoustic tokens of source audios to generate the synthetic audios. All the experiments are conducted on the monolingual SLU dataset SLURP and the multilingual SLU dataset MINDS-14. Experimental results show that our method outperforms the previous best Textless End-to-end SLU models and can obtain the comparable performance with the models trained with the assistance of the corresponding transcripts.
Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD), particularly with lengthy textual content. Existing studies primarily focus on real-world documents with sparse text, while challenges persist in comprehending the hierarchical semantic relations among multiple pages to locate multimodal components. The paper introduces PDF-MVQA, tailored for research journal articles, encompassing multiple pages and multimodal retrieval. Our approach aims to retrieve entire paragraphs containing answers or visually rich document entities like tables and figures. The main contribution is introducing a comprehensive PDF Document VQA dataset, allowing the examination of semantically hierarchical layout structures in text-dominant documents. We also present new VRD-QA frameworks to grasp textual contents and relations among document layouts simultaneously, extending page-level understanding to the entire multi-page document. We aim to enhance the capabilities of existing vision-and-language models in handling challenges posed by text-dominant documents in VRD-QA. Code and Appendix are in https://github.com/adlnlp/pdfmvqa
Cross-lingual named entity recognition (NER) aims to train an NER model for the target language leveraging only labeled source language data and unlabeled target language data. Prior approaches either perform label projection on translated source language data or employ a source model to assign pseudo labels for target language data and train a target model on these pseudo-labeled data to generalize to the target language. However, these automatic labeling procedures inevitably introduce noisy labels, thus leading to a performance drop. In this paper, we propose a Global-Local Denoising framework (GLoDe) for cross-lingual NER. Specifically, GLoDe introduces a progressive denoising strategy to rectify incorrect pseudo labels by leveraging both global and local distribution information in the semantic space. The refined pseudo-labeled target language data significantly improves the model's generalization ability. Moreover, previous methods only consider improving the model with language-agnostic features, however, we argue that target language-specific features are also important and should never be ignored. To this end, we employ a simple auxiliary task to achieve this goal. Experimental results on two benchmark datasets with six target languages demonstrate that our proposed GLoDe significantly outperforms current state-of-the-art methods.
The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to its powerful capability in generating utterances. However, there is a natural deficiency for such models, that is, inherent position bias, which may lead them to pay more attention to the nearby utterances instead of causally relevant ones, resulting in generating irrelevant and generic responses in long-term dialogue. To alleviate such problem, in this paper, we propose a novel method, named Causal Perception long-term Dialogue framework (CPD), which employs perturbation-based causal variable discovery method to extract casually relevant utterances from the dialogue history and enhances model causal perception during fine-tuning. Specifically, a local-position awareness method is proposed in CPD for inter-sentence position correlation elimination, which helps models extract causally relevant utterances based on perturbations. Then, a casual-perception fine-tuning strategy is also proposed, to enhance the capability of discovering the causal invariant factors, by differently perturbing causally relevant and non-casually relevant ones for response generation. Experimental results on two datasets prove that our proposed method can effectively alleviate the position bias for multiple LLMs and achieve significant progress compared with existing baselines.
Large Language Models have shown tremendous performance on a large variety of natural language processing tasks, ranging from text comprehension to common sense reasoning. However, the mechanisms responsible for this success remain opaque, and it is unclear whether LLMs can achieve human-like cognitive capabilities or whether these models are still fundamentally circumscribed. Abstract reasoning is a fundamental task for cognition, consisting of finding and applying a general pattern from few data. Evaluating deep neural architectures on this task could give insight into their potential limitations regarding reasoning and their broad generalisation abilities, yet this is currently an under-explored area. In this paper, we introduce a new benchmark for evaluating language models beyond memorization on abstract reasoning tasks. We perform extensive evaluations of state-of-the-art LLMs, showing that they currently achieve very limited performance in contrast with other natural language tasks, even when applying techniques that have been shown to improve performance on other NLP tasks. We argue that guiding LLM generation to follow causal paths could help improve the generalisation and reasoning abilities of LLMs.
We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skeleton transpilation and API keyword mapping. For code skeleton transpilation, it uses few-shot prompting on large language models (LLMs), while for API keyword mapping, it uses contextual embeddings from a code-specific BERT. These embeddings are trained in a domain-adversarial setup to generate a keyword translation dictionary. ADELT is trained on an unlabeled web-crawled deep learning corpus, without relying on any hand-crafted rules or parallel data. It outperforms state-of-the-art transpilers, improving pass@1 rate by 16.2 pts and 15.0 pts for PyTorch-Keras and PyTorch-MXNet transpilation pairs respectively. We provide open access to our code at https://github.com/gonglinyuan/adelt
Understanding the process of emotion generation is crucial for analyzing the causes behind emotions. Causal Emotion Entailment (CEE), an emotion-understanding task, aims to identify the causal utterances in a conversation that stimulate the emotions expressed in a target utterance. However, current works in CEE mainly focus on modeling semantic and emotional interactions in conversations, neglecting the exploration of the emotion-generation process. This hinders the models from deeply understanding emotions, restricting their ability to produce explainable predictions. In this work, inspired by the emotion generation process of "stimulus-appraisal-emotion" in the cognitive appraisal theory, we introduce a step-by-step reasoning method, Emotion-Cause Reasoning Chain (ECR-Chain), to infer the stimulus from the target emotional expressions in conversations. Specifically, we first introduce the ECR-Chain to ChatGPT via few-shot prompting, which significantly improves its performance on the CEE task. We further propose an automated construction process to utilize ChatGPT in building an ECR-Chain set, which can enhance the reasoning abilities of smaller models through supervised training and assist the Vicuna-7B model in achieving state-of-the-art CEE performance. Moreover, our methods can enable these generative language models to effectively perform emotion-cause reasoning in an explainable manner. Our code, data and more details are at https://github.com/hzp3517/ECR-Chain.
This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity simulations. The first level tests for language grounding by assessing a model's ability to relate simple textual descriptions with visual information. The second level evaluates the model's understanding of "Intuitive Physics" principles, such as object permanence and continuity. In addition to releasing the benchmark, we use it to evaluate several state-of-the-art multimodal LLMs. Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models. Although they exhibit at least some grounding capabilities, particularly for colors and shapes, these capabilities depend heavily on the prompting strategy. At the same time, all models perform below or at the chance level of 50% in the Intuitive Physics tests, while human subjects are on average 80% correct. These identified limitations underline the importance of using benchmarks like GRASP to monitor the progress of future models in developing these competencies.
Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations. This requires enumerating and labeling a long tail of user requests, which is challenging. At the same time, large language models (LLMs) encode knowledge about goals and plans that can help conversational assistants interpret user requests requiring numerous steps to complete. We introduce an approach to handle complex-intent-bearing utterances from a user via a process of hierarchical natural language decomposition and interpretation. Our approach uses a pre-trained language model to decompose a complex utterance into a sequence of simpler natural language steps and interprets each step using the language-to-program model designed for the interface. To test our approach, we collect and release DeCU —a new NL-to-program benchmark to evaluate Decomposition of Complex Utterances. Experiments show that the proposed approach enables the interpretation of complex utterances with almost no complex training data, while outperforming standard few-shot prompting approaches.
Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain consistent performance on complex hierarchically dependent tasks, especially when the downstream data is extremely scarce. The main challenge is how to transfer the unstructured semantic space in PLMs to the downstream domain hierarchy. Unlike previous work on hierarchical text classification (HTC) which directly performs multi-label classification or uses graph neural network (GNN) to inject label hierarchy, in this work, we study the HTC problem under a few-shot setting to adapt knowledge in PLMs from an unstructured manner to the downstream hierarchy. Technically, we design a simple yet effective method named Hierarchical Iterative Conditional Random Field (HierICRF) to search the most domain-challenging directions and exquisitely crafts domain-hierarchy adaptation as a hierarchical iterative language modeling problem, and then it encourages the model to make hierarchical consistency self-correction during the inference, thereby achieving knowledge transfer with hierarchical consistency preservation. We perform HierICRF on various architectures, and extensive experiments on two popular HTC datasets demonstrate that prompt with HierICRF significantly boosts the few-shot HTC performance with an average Micro-F1 by 28.80% to 1.50% and Macro-F1 by 36.29% to 1.5% over the previous state-of-the-art (SOTA) baselines under few-shot settings (1->16), while remaining SOTA hierarchical consistency performance.
Fine-tuning pre-trained large language models (LLMs) with limited hardware presents challenges due to GPU memory constraints. Various distributed fine-tuning methods have been proposed to alleviate memory constraints on GPU. However, determining the most effective method for achieving rapid fine-tuning while preventing GPU out-of-memory issues in a given environment remains unclear. To address this challenge, we introduce LLMem, a solution that estimates the GPU memory consumption when applying distributed fine-tuning methods across multiple GPUs and identifies the optimal method. We conduct GPU memory usage estimation prior to fine-tuning, leveraging the fundamental structure of transformer-based decoder models and the memory usage distribution of each method. Experimental results show that LLMem accurately estimates peak GPU memory usage on a single GPU, with an error rate of up to 1.6%. Additionally, it shows an average error rate of 3.0% when applying distributed fine-tuning methods to LLMs with more than a billion parameters on multi-GPU setups.
Cued Speech (CS) is an advanced visual phonetic encoding system that integrates lip reading with hand codings, enabling people with hearing impairments to communicate efficiently. CS video generation aims to produce specific lip and gesture movements of CS from audio or text inputs. The main challenge is that given limited CS data, we strive to simultaneously generate fine-grained hand and finger movements, as well as lip movements, meanwhile the two kinds of movements need to be asynchronously aligned. Existing CS generation methods are fragile and prone to poor performance due to template-based statistical models and careful hand-crafted pre-processing to fit the models. Therefore, we propose a novel Gloss-prompted Diffusion-based CS Gesture generation framework (called GlossDiff). Specifically, to integrate additional linguistic rules knowledge into the model. we first introduce a bridging instruction called Gloss, which is an automatically generated descriptive text to establish a direct and more delicate semantic connection between spoken language and CS gestures. Moreover, we first suggest rhythm is an important paralinguistic feature for CS to improve the communication efficacy. Therefore, we propose a novel Audio-driven Rhythmic Module (ARM) to learn rhythm that matches audio speech. Moreover, in this work, we design, record, and publish the first Chinese CS dataset with four CS cuers. Extensive experiments demonstrate that our method quantitatively and qualitatively outperforms current state-of-the-art (SOTA) methods. We will release the code and data at glossdiff.github.io/.
Spatial reasoning plays a vital role in both human cognition and machine intelligence, prompting new research into language models' (LMs) capabilities in this regard. However, existing benchmarks reveal shortcomings in evaluating qualitative spatial reasoning (QSR). These benchmarks typically present oversimplified scenarios or unclear natural language descriptions, hindering effective evaluation. We present a novel benchmark for assessing QSR in LMs, which is grounded in realistic 3D simulation data, offering a series of diverse room layouts with various objects and their spatial relationships. This approach provides a more detailed and context-rich narrative for spatial reasoning evaluation, diverging from traditional, toy-task-oriented scenarios. Our benchmark encompasses a broad spectrum of qualitative spatial relationships, including topological, directional, and distance relations. These are presented with different viewing points, varied granularities, and density of relation constraints to mimic real-world complexities. A key contribution is our logic-based consistency-checking tool, which enables the assessment of multiple plausible solutions, aligning with real-world scenarios where spatial relationships are often open to interpretation. Our benchmark evaluation of advanced LMs reveals their strengths and limitations in spatial reasoning. They face difficulties with multi-hop spatial reasoning and interpreting a mix of different view descriptions, pointing to areas for future improvement.
Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot learning, recent studies indicate that current LLMs still struggle with zero and few-shot RE. Previous studies are mainly dedicated to design prompt formats and select good examples for improving ICL-based RE. Although both factors are vital for ICL, if one can fundamentally boost the ICL capability of LLMs in RE, the zero and few-shot RE performance via ICL would be significantly improved. To this end, we introduce Micre (Meta In-Context learning of LLMs for Relation Extraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i.e., learning to learn in context for RE). Through meta-training, the model becomes more effectively to learn a new RE task in context by conditioning on a few training examples with no parameter updates or task-specific templates at inference time, enabling better zero and few-shot task generalization. We experiment Micre on various LLMs with different model scales and 12 public RE datasets, and then evaluate it on unseen RE benchmarks under zero and few-shot settings. Micre delivers comparable or superior performance compared to a range of baselines including supervised fine-tuning and typical in-context learning methods. We find that the gains are particular significant for larger model scales, and using a diverse set of the meta-training RE datasets is key to improvements. Empirically, we show that Micre can transfer the relation semantic knowledge via relation label name during inference on target RE datasets.
Dialogue relation extraction (DRE) aims to extract relations between two arguments within a dialogue, which is more challenging than standard RE due to the higher person pronoun frequency and lower information density in dialogues. However, existing DRE methods still suffer from two serious issues: (1) hard to capture long and sparse multi-turn information, and (2) struggle to extract golden relations based on partial dialogues, which motivates us to discover more effective methods that can alleviate the above issues. We notice that the rise of large language models (LLMs) has sparked considerable interest in evaluating their performance across diverse tasks. To this end, we initially investigate the capabilities of different LLMs in DRE, considering both proprietary models and open-source models. Interestingly, we discover that LLMs significantly alleviate two issues in existing DRE methods. Generally, we have following findings: (1) scaling up model size substantially boosts the overall DRE performance and achieves exceptional results, tackling the difficulty of capturing long and sparse multi-turn information; (2) LLMs encounter with much smaller performance drop from entire dialogue setting to partial dialogue setting compared to existing methods; (3) LLMs deliver competitive or superior performances under both full-shot and few-shot settings compared to current state-of-the-art; (4) LLMs show modest performances on inverse relations but much stronger improvements on general relations, and they can handle dialogues of various lengths especially for longer sequences.
Relation extraction (RE) aims to identify relations between entities mentioned in texts. Although large language models (LLMs) have demonstrated impressive in-context learning (ICL) abilities in various tasks, they still suffer from poor performances compared to most supervised fine-tuned RE methods. Utilizing ICL for RE with LLMs encounters two challenges: (1) retrieving good demonstrations from training examples, and (2) enabling LLMs exhibit strong ICL abilities in RE. On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations. On the other hand, ICL with an LLM achieves poor performance in RE while RE is different from language modeling in nature or the LLM is not large enough. In this work, we propose a novel recall-retrieve-reason RE framework that synergizes LLMs with retrieval corpora (training examples) to enable relevant retrieving and reliable in-context reasoning. Specifically, we distill the consistently ontological knowledge from training datasets to let LLMs generate relevant entity pairs grounded by retrieval corpora as valid queries. These entity pairs are then used to retrieve relevant training examples from the retrieval corpora as demonstrations for LLMs to conduct better ICL via instruction tuning. Extensive experiments on different LLMs and RE datasets demonstrate that our method generates relevant and valid entity pairs and boosts ICL abilities of LLMs, achieving competitive or new state-of-the-art performance on sentence-level RE compared to previous supervised fine-tuning methods and ICL-based methods.
The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE is limited by load imbalance and high latency of All-to-All communication, along with relatively redundant computation owing to large expert capacity. Load imbalance may result from existing routing policies that consistently tend to select certain experts. The frequent inter-node communication in the All-to-All procedure also significantly prolongs the training time. To alleviate the above performance problems, we propose a novel routing strategy that combines load balance and locality by converting partial inter-node communication to that of intra-node. Notably, we elucidate that there is a minimum threshold for expert capacity, calculated through the maximal angular deviation between the gating weights of the experts and the assigned tokens. We port these modifications on the PanGu-Σ model based on the MindSpore framework with multi-level routing and conduct experiments on Ascend clusters. The experiment results demonstrate that the proposed LocMoE reduces training time per epoch by 12.68% to 22.24% compared to classical routers, such as hash router and switch router, without impacting the model accuracy.
Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word representations. However, uncontrolled and over-replaced code-switching would augment dirty samples to model training. In other words, the excessive code-switching text samples will negatively hurt the models' cross-lingual transferability. To this end, we propose a Progressive Code-Switching (PCS) method to gradually generate moderately difficult code-switching examples for the model to discriminate from easy to hard. The idea is to incorporate progressively the preceding learned multilingual knowledge using easier code-switching data to guide model optimization on succeeding harder code-switching data. Specifically, we first design a difficulty measurer to measure the impact of replacing each word in a sentence based on the word relevance score. Then a code-switcher generates the code-switching data of increasing difficulty via a controllable temperature variable. In addition, a training scheduler decides when to sample harder code-switching data for model training. Experiments show our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.
The dynamic expansion of social media has led to an inundation of hateful memes on media platforms, accentuating the growing need for efficient identification and removal. Acknowledging the constraints of conventional multimodal hateful meme classification, which heavily depends on external knowledge and poses the risk of including irrelevant or redundant content, we developed Pen—a prompt-enhanced network framework based on the prompt learning approach. Specifically, after constructing the sequence through the prompt method and encoding it with a language model, we performed region information global extraction on the encoded sequence for multi-view perception. By capturing global information about inference instances and demonstrations, Pen facilitates category selection by fully leveraging sequence information. This approach significantly improves model classification accuracy. Additionally, to bolster the model's reasoning capabilities in the feature space, we introduced prompt-aware contrastive learning into the framework to improve the quality of sample feature distributions. Through extensive ablation experiments on two public datasets, we evaluate the effectiveness of the Pen framework, concurrently comparing it with state-of-the-art model baselines. Our research findings highlight that Pen surpasses manual prompt methods, showcasing superior generalization and classification accuracy in hateful meme classification tasks. Our code is available at https://github.com/juszzi/Pen.