Imagine AI assistants that enhance conversations without interrupting them: quietly providing relevant information during a medical consultation, seamlessly preparing materials as teachers discuss lesson plans, or unobtrusively scheduling meetings as colleagues debate calendars. While modern conversational LLM agents directly assist human users with tasks through a chat interface, we study this alternative paradigm for interacting with LLM agents, which we call "overhearing agents". Rather than demanding the user's attention, overhearing agents continuously monitor ambient activity and intervene only when they can provide contextual assistance. In this paper, we present the first analysis of overhearing LLM agents as a distinct paradigm in human-AI interaction and establish a taxonomy of overhearing agent interactions and tasks grounded in a survey of works on prior LLM-powered agents and exploratory HCI studies. Based on this taxonomy, we create a list of best practices for researchers and developers building overhearing agent systems. Finally, we outline the remaining research gaps and reveal opportunities for future research in the overhearing paradigm.

Arabic is one of the oldest languages still in use today. As a result, several Arabic-speaking regions have developed dialects that are unique to them. Dialect and emotion recognition have various uses in Arabic text analysis, such as determining an online customer's origin based on their comments. Furthermore, intelligent chatbots that are aware of a user's emotions can respond appropriately to the user. Current research in emotion detection in the Arabic language lacks awareness of how emotions are exhibited in different dialects, which motivates the work found in this study. This research addresses the problems of dialect and emotion classification in Arabic. Specifically, this is achieved by building a novel framework that can identify and predict Arabic dialects and emotions from a given text. The framework consists of three modules: A text-preprocessing module, a classification module, and a clustering module with the novel capability of building new dialect-aware emotion lexicons. The proposed framework generated a new emotional lexicon for different dialects. It achieved an accuracy of 88.9% in classifying Arabic dialects, which outperforms the state-of-the-art results by 6.45 percentage points. Furthermore, the framework achieved 89.1-79% accuracy in detecting emotions in the Egyptian and Gulf dialects, respectively.

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.

The most recent generation of chatbots has surfaced longstanding concerns about the growing sophistication and accessibility of artificial intelligence. Fears about the integrity of the job market -- from the creative economy to the managerial class -- have spread to the classroom as educators rethink learning in the wake of ChatGPT. Yet while apprehensions about employment and schools dominate headlines, the truth is that the effects of large-scale language models such as ChatGPT will touch virtually every corner of our lives. These new tools raise society-wide concerns about artificial intelligence's role in reinforcing social biases, committing fraud and identity theft, generating fake news, spreading misinformation and more. A team of researchers at the University of Pennsylvania School of Engineering and Applied Science is seeking to empower tech users to mitigate these risks.

If two sentences have the same meaning, it should follow that they are equivalent in their inferential properties, i.e., each sentence should textually entail the other. However, many paraphrase datasets currently in widespread use rely on a sense of paraphrase based on word overlap and syntax. Can we teach them instead to identify paraphrases in a way that draws on the inferential properties of the sentences, and is not over-reliant on lexical and syntactic similarities of a sentence pair? We apply the adversarial paradigm to this question, and introduce a new adversarial method of dataset creation for paraphrase identification: the Adversarial Paraphrasing Task (APT), which asks participants to generate semantically equivalent (in the sense of mutually implicative) but lexically and syntactically disparate paraphrases. These sentence pairs can then be used both to test paraphrase identification models (which get barely random accuracy) and then improve their performance. To accelerate dataset generation, we explore automation of APT using T5, and show that the resulting dataset also improves accuracy. We discuss implications for paraphrase detection and release our dataset in the hope of making paraphrase detection models better able to detect sentence-level meaning equivalence.

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can paraphrase without being bilingual. This work proposes to learn paraphrasing models from an unlabeled monolingual corpus only. To that end, we propose a residual variant of vector-quantized variational auto-encoder. We compare with MT-based approaches on paraphrase identification, generation, and training augmentation. Monolingual paraphrasing outperforms unsupervised translation in all settings. Comparisons with supervised translation are more mixed: monolingual paraphrasing is interesting for identification and augmentation; supervised translation is superior for generation.

In machine learning and deep learning we can't do anything without data. So the people that create datasets for us to train our models are the (often under-appreciated) heroes. Some of the most useful and important datasets are those that become important "academic baselines"; that is, datasets that are widely studied by researchers and used to compare algorithmic changes. Some of these become household names (at least, among households that train models!), such as MNIST, CIFAR 10, and Imagenet. We all owe a debt of gratitude to those kind folks who have made datasets available for the research community.

Facebook has begun using artificial intelligence to identify members that may be at risk of killing themselves. The social network has developed algorithms that spot warning signs in users' posts and the comments their friends leave in response. After confirmation by Facebook's human review team, the company contacts those thought to be at risk of self-harm to suggest ways they can seek help. A suicide helpline chief said the move was "not just helpful but critical". The tool is being tested only in the US at present.

Facebook has begun using artificial intelligence to identify members that may be at risk of killing themselves. The social network has developed algorithms that spot warning signs in users' posts and the comments their friends leave in response. After confirmation by Facebook's human review team, the company contacts those thought to be at risk of self-harm to suggest ways they can seek help. A suicide helpline chief said the move was "not just helpful but critical". The tool is being tested only in the US at present.

The new technique makes machine learning a little more like human learning; a more natural fit for natural language processing. In two separate experiments, the new method outperformed conventional machine learning techniques by about 10 percent. Conventional approaches to machine learning information extraction use vast amounts of training data, which increases the capacity of the system to handle difficult problems. The new approach uses much less data, which more realistically represents the amount of info typically available. The system then deals with the limited information in the same way a human would.