Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is a figure-out-as you go phenomena. To quickly bootstrap templates in a real-world setting, we need to induce template slots from documents with zero or minimal supervision. Since the purpose of question answering intersect with the goal of information extraction, we use automatic question generation to induce template slots from the documents and investigate how a tiny amount of a proxy human-supervision on-the-fly (termed as InteractiveIE) can further boost the performance. Extensive experiments on biomedical and legal documents, where obtaining training data is expensive, reveal encouraging trends of performance improvement using InteractiveIE over AI-only baseline.

Quantum state tomography (QST) is the process of reconstructing the state of a quantum system (mathematically described as a density matrix) through a series of different measurements, which can be solved by learning a parameterized function to translate experimentally measured statistics into physical density matrices. However, the specific structure of quantum measurements for characterizing a quantum state has been neglected in previous work. In this paper, we explore the similarity between highly structured sentences in natural language and intrinsically structured measurements in QST. To fully leverage the intrinsic quantum characteristics involved in QST, we design a quantum-aware transformer (QAT) model to capture the complex relationship between measured frequencies and density matrices. In particular, we query quantum operators in the architecture to facilitate informative representations of quantum data and integrate the Bures distance into the loss function to evaluate quantum state fidelity, thereby enabling the reconstruction of quantum states from measured data with high fidelity. Extensive simulations and experiments (on IBM quantum computers) demonstrate the superiority of the QAT in reconstructing quantum states with favorable robustness against experimental noise.

Recommender systems are ubiquitous yet often difficult for users to control, and adjust if recommendation quality is poor. This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback. However, as with most application domains, building robust CRSs requires training data that reflects system usage$\unicode{x2014}$here conversations with user utterances paired with items that cover a wide range of preferences. This has proved challenging to collect scalably using conventional methods. We address the question of whether it can be generated synthetically, building on recent advances in natural language. We evaluate in the setting of item set recommendation, noting the increasing attention to this task motivated by use cases like music, news, and recipe recommendation. We present TalkTheWalk, which synthesizes realistic high-quality conversational data by leveraging domain expertise encoded in widely available curated item collections, generating a sequence of hypothetical yet plausible item sets, then using a language model to produce corresponding user utterances. We generate over one million diverse playlist curation conversations in the music domain, and show these contain consistent utterances with relevant item sets nearly matching the quality of an existing but small human-collected dataset for this task. We demonstrate the utility of the generated synthetic dataset on a conversational item retrieval task and show that it improves over both unsupervised baselines and systems trained on a real dataset.

Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generating narratives over time, and critically lack basic commonsense reasoning. Furthermore, existing methods generally focus only on single-character stories, or fail to track characters at all. To improve the coherence of generated narratives and to expand the scope of character-centric narrative generation, we introduce Commonsense-inference Augmented neural StoryTelling (CAST), a framework for introducing commonsense reasoning into the generation process with the option to model the interaction between multiple characters. We find that our CAST method produces significantly more coherent, on-topic, enjoyable and fluent stories than existing models in both the single-character and two-character settings in three storytelling domains.

This story originally appeared in New York Focus, a nonprofit news publication investigating power in New York. Vigilante violence is at an all-time high in the occupied West Bank. Emboldened by the war in the Gaza Strip and backed by the military, Israeli settlers aiming to annex more and more of the Palestinian territory have launched hundreds of attacks, displacing people from at least 17 communities over the past month while soldiers and settlers have killed nearly 200. And at least three New York nonprofit organizations are calling on donors to help outfit those settlers with combat gear, in a fundraising blitz funneling millions of tax-deductible dollars to the West Bank aggression. By chipping into a "thermal drone matching campaign," donors can help the Long Island–based One Israel Fund buy remote-controlled aerial vehicles for settler militias.

It's been widely touted as a replacement for the smartphone, but it seems Humane's AI Pin isn't quite so smart after all. In a promotional video released to launch the product, the device made not just one, but two blunders. In the video, founders Imran Chaudhri and Bethany Bongiorno asked the device seemingly simple questions. Embarrassingly, the $699 (£564) AI Pin incorrectly identified the best location to view the next solar eclipse, as well as the nutritional value of a handful of almonds. In an embarrassing back-step, the company has now released an edited version of the video, and claims the errors were the result of a'glitch.'

Lachlan Murdoch will become the sole chair of both companies in November. As Rupert Murdoch marked his final day as Executive Chairman of News Corp on Wednesday, the media icon saluted his son Lachlan as the right man to lead the company forward. "Lachlan is a principled leader, and a believer in the social purpose of journalism. I hope to continue an active role in the company," Rupert Murdoch said during the company's annual shareholders meeting. Rupert Murdoch, 92, will now be Chairman Emeritus of FOX Corporation and News Corp; he will mark his final day at the former on Friday.

In multi-objective (MO) heuristic search, solution costs, as well as heuristic values, are sets of multi-dimensional cost vectors, representing possible non-dominated trade-offs between objectives. The maximum of two or more such vector sets, which is an important operation in creating informative admissible MO heuristics, can be defined in several ways: Geißer et al. recently proposed two MO maximum operators, the component-wise maximum (comax) and the anti-dominance maximum (admax), which represent different trade-offs between informativeness and computational cost. We show that the anti-dominance maximum is not admissibility-preserving, and propose an alternative, the "select one" maximum (somax). We also show that the comax operator is the greatest admissibility-preserving MO maximum, and briefly investigate its efficient implementation. The conclusion of our experimental results is that somax achieves a trade-off similar to that intended with admax - cheaper to compute but less informed - also when compared to an improved comax implementation.

Traditional Korean medicine (TKM) emphasizes individualized diagnosis and treatment. This uniqueness makes AI modeling difficult due to limited data and implicit processes. Large language models (LLMs) have demonstrated impressive medical inference, even without advanced training in medical texts. This study assessed the capabilities of GPT-4 in TKM, using the Korean National Licensing Examination for Korean Medicine Doctors (K-NLEKMD) as a benchmark. The K-NLEKMD, administered by a national organization, encompasses 12 major subjects in TKM. We optimized prompts with Chinese-term annotation, English translation for questions and instruction, exam-optimized instruction, and self-consistency. GPT-4 with optimized prompts achieved 66.18% accuracy, surpassing both the examination's average pass mark of 60% and the 40% minimum for each subject. The gradual introduction of language-related prompts and prompting techniques enhanced the accuracy from 51.82% to its maximum accuracy. GPT-4 showed low accuracy in subjects including public health & medicine-related law, internal medicine (2) which are localized in Korea and TKM. The model's accuracy was lower for questions requiring TKM-specialized knowledge. It exhibited higher accuracy in diagnosis-based and recall-based questions than in intervention-based questions. A positive correlation was observed between the consistency and accuracy of GPT-4's responses. This study unveils both the potential and challenges of applying LLMs to TKM. These findings underline the potential of LLMs like GPT-4 in culturally adapted medicine, especially TKM, for tasks such as clinical assistance, medical education, and research. But they also point towards the necessity for the development of methods to mitigate cultural bias inherent in large language models and validate their efficacy in real-world clinical settings.

People share stories online for a myriad of purposes, whether as a means of self-disclosure, processing difficult personal experiences, providing needed information or entertainment, or persuading others to share their beliefs. Better understanding of online storytelling can illuminate the dynamics of social movements, sensemaking practices, persuasion strategies, and more. However, unlike other media such as books and visual content where the narrative nature of the content is often overtly signaled at the document level, studying storytelling in online communities is challenging due to the mixture of storytelling and non-storytelling behavior, which can be interspersed within documents and across diverse topics and settings. We introduce a codebook and create the Storytelling in Online Communities Corpus, an expert-annotated dataset of 502 English-language posts and comments with labeled story and event spans. Using our corpus, we train and evaluate an online story detection model, which we use to investigate the role storytelling of in different social contexts. We identify distinctive features of online storytelling, the prevalence of storytelling among different communities, and the conversational patterns of storytelling.