Jailbreaking? One Step Is Enough!

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However, current jailbreak methods and the target model's defenses are engaged in an independent and adversarial process, resulting in the need for frequent attack iterations and redesigning attacks for different models. To address these gaps, we propose a Reverse Embedded Defense Attack (REDA) mechanism that disguises the attack intention as the "defense". intention against harmful content. Specifically, REDA starts from the target response, guiding the model to embed harmful content within its defensive measures, thereby relegating harmful content to a secondary role and making the model believe it is performing a defensive task. The attacking model considers that it is guiding the target model to deal with harmful content, while the target model thinks it is performing a defensive task, creating an illusion of cooperation between the two. Additionally, to enhance the model's confidence and guidance in "defensive" intentions, we adopt in-context learning (ICL) with a small number of attack examples and construct a corresponding dataset of attack examples. Extensive evaluations demonstrate that the REDA method enables cross-model attacks without the need to redesign attack strategies for different models, enables successful jailbreak in one iteration, and outperforms existing methods on both open-source and closed-source models.

A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction

Currently, the majority of research in grammatical error correction (GEC) is concentrated on universal languages, such as English and Chinese. Many low-resource languages lack accessible evaluation corpora. How to efficiently construct high-quality evaluation corpora for GEC in low-resource languages has become a significant challenge. To fill these gaps, in this paper, we present a framework for constructing GEC corpora. Specifically, we focus on Indonesian as our research language and construct an evaluation corpus for Indonesian GEC using the proposed framework, addressing the limitations of existing evaluation corpora in Indonesian. Furthermore, we investigate the feasibility of utilizing existing large language models (LLMs), such as GPT-3.5-Turbo and GPT-4, to streamline corpus annotation efforts in GEC tasks. The results demonstrate significant potential for enhancing the performance of LLMs in low-resource language settings. Our code and corpus can be obtained from https://github.com/GKLMIP/GEC-Construction-Framework.

HateDebias: On the Diversity and Variability of Hate Speech Debiasing

Hate speech on social media is ubiquitous but urgently controlled. Without detecting and mitigating the biases brought by hate speech, different types of ethical problems. While a number of datasets have been proposed to address the problem of hate speech detection, these datasets seldom consider the diversity and variability of bias, making it far from real-world scenarios. To fill this gap, we propose a benchmark, named HateDebias, to analyze the model ability of hate speech detection under continuous, changing environments. Specifically, to meet the diversity of biases, we collect existing hate speech detection datasets with different types of biases. To further meet the variability (i.e., the changing of bias attributes in datasets), we reorganize datasets to follow the continuous learning setting. We evaluate the detection accuracy of models trained on the datasets with a single type of bias with the performance on the HateDebias, where a significant performance drop is observed. To provide a potential direction for debiasing, we further propose a debiasing framework based on continuous learning and bias information regularization, as well as the memory replay strategies to ensure the debiasing ability of the model. Experiment results on the proposed benchmark show that the aforementioned method can improve several baselines with a distinguished margin, highlighting its effectiveness in real-world applications.

An interpretability framework for Similar case matching

Similar Case Matching (SCM) is designed to determine whether two cases are similar. The task has an essential role in the legal system, helping legal professionals to find relevant cases quickly and thus deal with them more efficiently. Existing research has focused on improving the model's performance but not on its interpretability. Therefore, this paper proposes a pipeline framework for interpretable SCM, which consists of four modules: a judicial feature sentence identification module, a case matching module, a feature sentence alignment module, and a conflict disambiguation module. Unlike existing SCM methods, our framework will identify feature sentences in a case that contain essential information, perform similar case matching based on the extracted feature sentence results, and align the feature sentences in the two cases to provide evidence for the similarity of the cases. SCM results may conflict with feature sentence alignment results, and our framework further disambiguates against this inconsistency. The experimental results show the effectiveness of our framework, and our work provides a new benchmark for interpretable SCM.

A BERT-based Unsupervised Grammatical Error Correction Framework

Grammatical error correction (GEC) is a challenging task of natural language processing techniques. While more attempts are being made in this approach for universal languages like English or Chinese, relatively little work has been done for low-resource languages for the lack of large annotated corpora. In low-resource languages, the current unsupervised GEC based on language model scoring performs well. However, the pre-trained language model is still to be explored in this context. This study proposes a BERT-based unsupervised GEC framework, where GEC is viewed as multi-class classification task. The framework contains three modules: data flow construction module, sentence perplexity scoring module, and error detecting and correcting module. We propose a novel scoring method for pseudo-perplexity to evaluate a sentence's probable correctness and construct a Tagalog corpus for Tagalog GEC research. It obtains competitive performance on the Tagalog corpus we construct and open-source Indonesian corpus and it demonstrates that our framework is complementary to baseline method for low-resource GEC task.

Model and Evaluation: Towards Fairness in Multilingual Text Classification

Recently, more and more research has focused on addressing bias in text classification models. However, existing research mainly focuses on the fairness of monolingual text classification models, and research on fairness for multilingual text classification is still very limited. In this paper, we focus on the task of multilingual text classification and propose a debiasing framework for multilingual text classification based on contrastive learning. Our proposed method does not rely on any external language resources and can be extended to any other languages. The model contains four modules: multilingual text representation module, language fusion module, text debiasing module, and text classification module. The multilingual text representation module uses a multilingual pre-trained language model to represent the text, the language fusion module makes the semantic spaces of different languages tend to be consistent through contrastive learning, and the text debiasing module uses contrastive learning to make the model unable to identify sensitive attributes' information. The text classification module completes the basic tasks of multilingual text classification. In addition, the existing research on the fairness of multilingual text classification is relatively simple in the evaluation mode. The evaluation method of fairness is the same as the monolingual equality difference evaluation method, that is, the evaluation is performed on a single language. We propose a multi-dimensional fairness evaluation framework for multilingual text classification, which evaluates the model's monolingual equality difference, multilingual equality difference, multilingual equality performance difference, and destructiveness of the fairness strategy. We hope that our work can provide a more general debiasing method and a more comprehensive evaluation framework for multilingual text fairness tasks.

Research on the application of contrastive learning in multi-label text classification

The effective application of contrastive learning technology in natural language processing tasks shows the superiority of contrastive learning in text analysis tasks. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive learning. Since it is difficult to construct contrastive objects in multi-label multi-classification tasks, there are few contrastive losses for multi-label multi-classification text classification. In this paper, we propose five contrastive losses for multi-label multi-classification tasks. They are Strict Contrastive Loss (SCL), Intra-label Contrastive Loss (ICL), Jaccard Similarity Contrastive Loss (JSCL), and Jaccard Similarity Probability Contrastive Loss (JSPCL) and Stepwise Label Contrastive Loss (SLCL). We explore the effectiveness of contrastive learning for multi-label multi-classification tasks under different strategies, and provide a set of baseline methods for contrastive learning techniques on multi-label classification tasks. We also perform an interpretability analysis of our approach to show how different contrastive learning methods play their roles. The experimental results in this paper demonstrate that our proposed contrastive losses can bring some improvement for multi-label multi-classification tasks. Our work reveal how to "appropriately" change the contrastive way of contrastive learning is the key idea to improve the adaptability of contrastive learning in multi-label multi-classification tasks.

A Chinese Spelling Check Framework Based on Reverse Contrastive Learning

Chinese spelling check is a task to detect and correct spelling mistakes in Chinese text. Existing research aims to enhance the text representation and use multi-source information to improve the detection and correction capabilities of models, but does not pay too much attention to improving their ability to distinguish between confusable words. Contrastive learning, whose aim is to minimize the distance in representation space between similar sample pairs, has recently become a dominant technique in natural language processing. Inspired by contrastive learning, we present a novel framework for Chinese spelling checking, which consists of three modules: language representation, spelling check and reverse contrastive learning. Specifically, we propose a reverse contrastive learning strategy, which explicitly forces the model to minimize the agreement between the similar examples, namely, the phonetically and visually confusable characters. Experimental results show that our framework is model-agnostic and could be combined with existing Chinese spelling check models to yield state-of-the-art performance.

CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

As an extensive research in the field of Natural language processing (NLP), aspect-based sentiment analysis (ABSA) is the task of predicting the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack of sufficient annotation resources, thus more and more recent researchers focus on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent researches only concentrate on cross-lingual data alignment instead of model alignment. To this end, we propose a novel framework, CL-XABSA: Contrastive Learning for Cross-lingual Aspect-Based Sentiment Analysis. Specifically, we design two contrastive strategies, token level contrastive learning of token embeddings (TL-CTE) and sentiment level contrastive learning of token embeddings (SL-CTE), to regularize the semantic space of source and target language to be more uniform. Since our framework can receive datasets in multiple languages during training, our framework can be adapted not only for XABSA task, but also for multilingual aspect-based sentiment analysis (MABSA). To further improve the performance of our model, we perform knowledge distillation technology leveraging data from unlabeled target language. In the distillation XABSA task, we further explore the comparative effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three tasks of XABSA, distillation XABSA and MABSA. For reproducibility, our code for this paper is available at https://github.com/GKLMIP/CL-XABSA.