In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for question-answering pairs, providing distinct perspectives on these coupled attributes. Overall, we provide 44.6k refined prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels ranging from minor to severe, with answers generated by Llama-family models. Based on this, we collected 166.8k preference data, including dual-preference (helpfulness and harmlessness decoupled) and single-preference data (trade-off the helpfulness and harmlessness from scratch), respectively. Using the large-scale annotation data, we further train severity-sensitive moderation for the risk control of LLMs and safety-centric RLHF algorithms for the safety alignment of LLMs. We believe this dataset will be a valuable resource for the community, aiding in the safe deployment of LLMs.

Our research introduces an innovative Natural Language Generation (NLG) approach that aims to optimize user experience and alleviate the workload of human customer support agents. Our primary objective is to generate informal summaries for online articles and posts using an offline reinforcement learning technique. In our study, we compare our proposed method with existing approaches to text generation and provide a comprehensive overview of our architectural design, which incorporates crawling, reinforcement learning, and text generation modules. By presenting this original approach, our paper makes a valuable contribution to the field of NLG by offering a fresh perspective on generating natural language summaries for online content. Through the implementation of Empowering NLG, we are able to generate higher-quality replies in the online domain. The experimental results demonstrate a significant improvement in the average "like" score, increasing from 0.09954378 to 0.5000152. This advancement has the potential to enhance the efficiency and effectiveness of customer support services and elevate the overall user experience when consuming online content.

The multi-armed bandit (MAB) model is one of the most classical models to study decision-making in an uncertain environment. In this model, a player chooses one of $K$ possible arms of a bandit machine to play at each time step, where the corresponding arm returns a random reward to the player, potentially from a specific unknown distribution. The target of the player is to collect as many rewards as possible during the process. Despite its simplicity, the MAB model offers an excellent playground for studying the trade-off between exploration versus exploitation and designing effective algorithms for sequential decision-making under uncertainty. Although many asymptotically optimal algorithms have been established, the finite-time behaviors of the stochastic dynamics of the MAB model appear much more challenging to analyze, due to the intertwine between the decision-making and the rewards being collected. In this paper, we employ techniques in statistical physics to analyze the MAB model, which facilitates the characterization of the distribution of cumulative regrets at a finite short time, the central quantity of interest in an MAB algorithm, as well as the intricate dynamical behaviors of the model. Our analytical results, in good agreement with simulations, point to the emergence of an interesting multimodal regret distribution, with large regrets resulting from excess exploitation of sub-optimal arms due to an initial unlucky output from the optimal one.

To provide consistent emotional interaction with users, dialog systems should be capable to automatically select appropriate emotions for responses like humans. However, most existing works focus on rendering specified emotions in responses or empathetically respond to the emotion of users, yet the individual difference in emotion expression is overlooked. This may lead to inconsistent emotional expressions and disinterest users. To tackle this issue, we propose to equip the dialog system with personality and enable it to automatically select emotions in responses by simulating the emotion transition of humans in conversation. In detail, the emotion of the dialog system is transitioned from its preceding emotion in context. The transition is triggered by the preceding dialog context and affected by the specified personality trait. To achieve this, we first model the emotion transition in the dialog system as the variation between the preceding emotion and the response emotion in the Valence-Arousal-Dominance (VAD) emotion space. Then, we design neural networks to encode the preceding dialog context and the specified personality traits to compose the variation. Finally, the emotion for response is selected from the sum of the preceding emotion and the variation. We construct a dialog dataset with emotion and personality labels and conduct emotion prediction tasks for evaluation. Experimental results validate the effectiveness of the personality-affected emotion transition.

Cross-domain sentiment classification aims to tag sentiments for a target domain by labeled data from a source domain. Due to the difference between domains, the accuracy of a trained classifier may be very low. In this paper, we propose a boosting-based learning framework named TR-TrAdaBoost for cross-domain sentiment classification. We firstly explore the topic distribution of documents, and then combine it with the unigram TrAdaBoost. The topic distribution captures the domain information of documents, which is valuable for cross-domain sentiment classification. Experimental results indicate that TR-TrAdaBoost represents documents well and boost the performance and robustness of TrAdaBoost.

A common problem for companies with strong business growth is that it is hard to find enough experienced staff to support expansion needs. This problem is particular pronounced for operations planners and controllers who must be very highly knowledgeable and experienced with the business domain. This article is a case study of how one of the largest travel agencies in Hong Kong alleviated this problem by using AI to support decision-making and problem-solving so that their planners and controllers can work more effectively and efficiently to sustain business growth while maintaining consistent quality of service. AI is used in a mission critical fleet management system (FMS) that supports the scheduling and management of a fleet of luxury limousines for business travelers. The AI problem was modeled as a constraint satisfaction problem (CSP). The use of AI enabled the travel agency to sign up additional hotel partners, handle more orders and expand their fleet with their existing team of planners and controllers. Using modern web 2.0 architecture and proven AI technology, we were able to achieve low-risk implementation and deployment success with concrete and measurable business benefits.