Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as jailbreaking, leading to unintended behaviors. In this work, we propose a novel black-box jailbreak framework for automated red teaming of LLMs. We designed malicious content concealing and memory reframing with an iterative optimization algorithm to jailbreak LLMs, motivated by the research about the distractibility and over-confidence phenomenon of LLMs. Extensive experiments of jailbreaking both open-source and proprietary LLMs demonstrate the superiority of our framework in terms of effectiveness, scalability and transferability. We also evaluate the effectiveness of existing jailbreak defense methods against our attack and highlight the crucial need to develop more effective and practical defense strategies.

Data augmentation methods have been a promising direction to improve the performance of small models for low-resource dialogue state tracking. However, traditional methods rely on pre-defined user goals and neglect the importance of data complexity in this task. In this paper, we propose EDZ-DA, an Easy-to-Difficult Zero-shot Data Augmentation framework for low-resource dialogue state tracking that utilizes large language models to automatically catch the relationships of different domains and then generate the dialogue data. We also complicate the dialogues based on the domain relation to enhance the model’s capability for co-reference slot tracking. Furthermore, we permute slot values to mitigate the influence of output orders and the problem of incomplete value generation. Experimental results illustrate the superiority of our proposed method compared to previous strong data augmentation baselines on MultiWOZ.

Knowledge base (KB) embeddings have been shown to contain gender biases. In this paper, we study two questions regarding these biases: how to quantify them, and how to trace their origins in KB? Specifically, first, we develop two novel bias measures respectively for a group of person entities and an individual person entity. Evidence of their validity is observed by comparison with real-world census data. Second, we use the influence function to inspect the contribution of each triple in KB to the overall group bias. To exemplify the potential applications of our study, we also present two strategies (by adding and removing KB triples) to mitigate gender biases in KB embeddings.

Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation. It is beneficial to divide up, such conversations with multiple subgoals (such as social chat, question answering, recommendation, etc.), so that the system can retrieve appropriate knowledge with better accuracy under different subgoals. In this paper, we propose a unified framework for common knowledge-based multi-subgoal dialog: knowledge-enhanced multi-subgoal driven recommender system (KERS). We first predict a sequence of subgoals and use them to guide the dialog model to select knowledge from a sub-set of existing knowledge graph. We then propose three new mechanisms to filter noisy knowledge and to enhance the inclusion of cleaned knowledge in the dialog response generation process. Experiments show that our method obtains state-of-the-art results on DuRecDial dataset in both automatic and human evaluation.

The classic deep learning paradigm learns a model from the training data of a single task and the learned model is also tested on the same task. This paper studies the problem of learning a sequence of tasks (sentiment classification tasks in our case). After each sentiment classification task is learned, its knowledge is retained to help future task learning. Following this setting, we explore attention neural networks and propose a Bayes-enhanced Lifelong Attention Network (BLAN). The key idea is to exploit the generative parameters of naive Bayes to learn attention knowledge. The learned knowledge from each task is stored in a knowledge base and later used to build lifelong attentions. The constructed lifelong attentions are then used to enhance the attention of the network to help new task learning. Experimental results on product reviews from Amazon.com show the effectiveness of the proposed model.

Dialogue state tracker is responsible for inferring user intentions through dialogue history. Previous methods have difficulties in handling dialogues with long interaction context, due to the excessive information. We propose a Dialogue State Tracker with Slot Attention and Slot Information Sharing (SAS) to reduce redundant information’s interference and improve long dialogue context tracking. Specially, we first apply a Slot Attention to learn a set of slot-specific features from the original dialogue and then integrate them using a slot information sharing module. Our model yields a significantly improved performance compared to previous state-of the-art models on the MultiWOZ dataset.

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting ‘clean’ labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.

A CNN method for sentiment classification task in Task 4A of SemEval 2017 is presented. To solve the problem of word2vec training word vector slowly, a method of training word vector by integrating word2vec and Convolutional Neural Network (CNN) is proposed. This training method not only improves the training speed of word2vec, but also makes the word vector more effective for the target task. Furthermore, the word2vec adopts a full connection between the input layer and the projection layer of the Continuous Bag-of-Words (CBOW) for acquiring the semantic information of the original sentence.