We present UniDetox, a universally applicable method designed to mitigate toxicity across various large language models (LLMs). Previous detoxification methods are typically model-specific, addressing only individual models or model families, and require careful hyperparameter tuning due to the trade-off between detoxification efficacy and language modeling performance. In contrast, UniDetox provides a detoxification technique that can be universally applied to a wide range of LLMs without the need for separate model-specific tuning. Specifically, we propose a novel and efficient dataset distillation technique for detoxification using contrastive decoding. This approach distills detoxifying representations in the form of synthetic text data, enabling universal detoxification of any LLM through fine-tuning with the distilled text. Our experiments demonstrate that the detoxifying text distilled from GPT-2 can effectively detoxify larger models, including OPT, Falcon, and LLaMA-2. Furthermore, UniDetox eliminates the need for separate hyperparameter tuning for each model, as a single hyperparameter configuration can be seamlessly applied across different models. Additionally, analysis of the detoxifying text reveals a reduction in politically biased content, providing insights into the attributes necessary for effective detoxification of LLMs.

Abstract This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys generic content, and the leaf sentences describe specific topics. Experimental results demonstrate that the generated topic sentences are appropriate as a summary of opinionated texts, which are more informative and cover more input contents than those generated by the recent unsupervised summarization model (Bražinskas et al., 2020). Furthermore, we demonstrate that the variance of latent Gaussians represents the granularity of sentences, analogous to Gaussian word embedding (Vilnis and McCallum, 2015).

This paper presents a tree-structured neural topic model, which has a topic distribution over a tree with an infinite number of branches.Our model parameterizes an unbounded ancestral and fraternal topic distribution by applying doubly-recurrent neural networks.With the help of autoencoding variational Bayes, our model improves data scalability and achieves competitive performance when inducing latent topics and tree structures, as compared to a prior tree-structured topic model (Blei et al., 2010).This work extends the tree-structured topic model such that it can be incorporated with neural models for downstream tasks.

This paper focuses on the end-to-end abstractive summarization of a single product review without supervision.We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent in detail.By recursively estimating a parent from its children, our model learns the latent discourse tree without an external parser and generates a concise summary.We also introduce an architecture that ranks the importance of each sentence on the tree to support summary generation focusing on the main review point.The experimental results demonstrate that our model is competitive with or outperforms other unsupervised approaches.In particular, for relatively long reviews, it achieves a competitive or better performance than supervised models.The induced tree shows that the child sentences provide additional information about their parent, and the generated summary abstracts the entire review.

The need for automatic document summarization that can be used for practical applications is increasing rapidly.In this paper, we propose a general framework for summarization that extracts sentences from a document using externally related information.Our work is aimed at single document summarization using small amounts of reference summaries.In particular, we address document summarization in the framework of multitask learning using curriculum learning for sentence extraction and document classification.The proposed framework enables us to obtain better feature representations to extract sentences from documents.We evaluate our proposed summarization method on two datasets: financial report and news corpus.Experimental results demonstrate that our summarizers achieve performance that is comparable to stateof-the-art systems.

Abstract Online communication is an indispensable tool for communication and management. The network structure of communication is considered to affect team and individual performances, but it has not been not empirically tested. In this article, we collected a set of 1‐month e‐mail logs of a company and conducted an e‐mail network analysis. We calculated the network centralities of 72 managerial candidates, and investigated the relationship between positions in the network and leadership performance with partial least squares structural equation modeling. Betweenness and in‐degree network centralities of those middle managers are correlated with their leadership performance; on the other hand, for this management group, out‐degree has no correlation, and PageRank is a negative indicator of leadership. Leaders with high performance are trusted in their communities as a hub of the information channel of the communication network.

Selecting relevant people is crucial for collaborative systems exploiting other users' experiences. With the new developments of the Web and ubiquitous technologies, various user data may support people selection. Given the wide range of user data sources, the question is now how to select appropriate users meeting the information seeker's goal. We propose recommendations for the design of people search interfaces, providing an overview of the user data and tools of relevance and two examples of how such recommendations can be met in one single interface, ensuring the selection of appropriate and reachable people. We also show applications of people search interfaces in different scenarios.

Social networks play important roles in the Semantic Web: knowledge management, information retrieval, ubiquitous computing, and so on. We propose a social network extraction system called POLYPHONET, which employs several advanced techniques to extract relations of persons, detect groups of persons, and obtain keywords for a person. Search engines, especially Google, are used to measure co-occurrence of information and obtain Web documents.Several studies have used search engines to extract social networks from the Web, but our research advances the following points: First, we reduce the related methods into simple pseudocodes using Google so that we can build up integrated systems. Second, we develop several new algorithms for social networking mining such as those to classify relations into categories, to make extraction scalable, and to obtain and utilize person-to-word relations. Third, every module is implemented in POLYPHONET, which has been used at four academic conferences, each with more than 500 participants. We overview that system. Finally, a novel architecture called Super Social Network Mining is proposed; it utilizes simple modules using Google and is characterized by scalability and Relate-Identify processes: Identification of each entity and extraction of relations are repeated to obtain a more precise social network.

While users disseminate various information in the open and widely distributed environment of the Semantic Web, determination of who shares access to particular information is at the center of looming privacy concerns. We propose a real-world-oriented information sharing system that uses social networks. The system automatically obtains users' social relationships by mining various external sources. It also enables users to analyze their social networks to provide awareness of the information dissemination process. Users can determine who has access to particular information based on the social relationships and network analysis.