Information Retrieval (IR) systems are crucial tools for users to access information, widely applied in scenarios like search engines, question answering, and recommendation systems. Traditional IR methods, based on similarity matching to return ranked lists of documents, have been reliable means of information acquisition, dominating the IR field for years. With the advancement of pre-trained language models, generative information retrieval (GenIR) has emerged as a novel paradigm, gaining increasing attention in recent years. Currently, research in GenIR can be categorized into two aspects: generative document retrieval (GR) and reliable response generation. GR leverages the generative model's parameters for memorizing documents, enabling retrieval by directly generating relevant document identifiers without explicit indexing. Reliable response generation, on the other hand, employs language models to directly generate the information users seek, breaking the limitations of traditional IR in terms of document granularity and relevance matching, offering more flexibility, efficiency, and creativity, thus better meeting practical needs. This paper aims to systematically review the latest research progress in GenIR. We will summarize the advancements in GR regarding model training, document identifier, incremental learning, downstream tasks adaptation, multi-modal GR and generative recommendation, as well as progress in reliable response generation in aspects of internal knowledge memorization, external knowledge augmentation, generating response with citations and personal information assistant. We also review the evaluation, challenges and future prospects in GenIR systems. This review aims to offer a comprehensive reference for researchers in the GenIR field, encouraging further development in this area.

This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or justifications for their veracity assessments. We examine the effectiveness of zero/few-shot prompting and parameter-efficient fine-tuning across various open and closed-source models, examining their performance in both isolated and joint tasks of veracity prediction and explanation generation. Importantly, we employ a dual evaluation approach comprising previously established automatic metrics and a novel set of criteria through human evaluation. Our automatic evaluation indicates that, within the zero-shot scenario, GPT-4 emerges as the standout performer, but in few-shot and parameter-efficient fine-tuning contexts, open-source models demonstrate their capacity to not only bridge the performance gap but, in some instances, surpass GPT-4. Human evaluation reveals yet more nuance as well as indicating potential problems with the gold explanations.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, T2/FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

The rapid advancement of AI technologies yields numerous future impacts on individuals and society. Policy-makers are therefore tasked to react quickly and establish policies that mitigate those impacts. However, anticipating the effectiveness of policies is a difficult task, as some impacts might only be observable in the future and respective policies might not be applicable to the future development of AI. In this work we develop a method for using large language models (LLMs) to evaluate the efficacy of a given piece of policy at mitigating specified negative impacts. We do so by using GPT-4 to generate scenarios both pre- and post-introduction of policy and translating these vivid stories into metrics based on human perceptions of impacts. We leverage an already established taxonomy of impacts of generative AI in the media environment to generate a set of scenario pairs both mitigated and non-mitigated by the transparency legislation of Article 50 of the EU AI Act. We then run a user study (n=234) to evaluate these scenarios across four risk-assessment dimensions: severity, plausibility, magnitude, and specificity to vulnerable populations. We find that this transparency legislation is perceived to be effective at mitigating harms in areas such as labor and well-being, but largely ineffective in areas such as social cohesion and security. Through this case study on generative AI harms we demonstrate the efficacy of our method as a tool to iterate on the effectiveness of policy on mitigating various negative impacts. We expect this method to be useful to researchers or other stakeholders who want to brainstorm the potential utility of different pieces of policy or other mitigation strategies.

Can a video game writer do her best work at the industry's biggest scale? Well: Meghna Jayanth is fine where she is. Last year, with Outerloop Games, she released Thirsty Suitors, a fluorescent fusion of messy flirting and sick skating; coming up next is All Rise, a climate action courtroom drama. These are indie games – Thirsty Suitors' hero is a queer Desi skater and the villain is her feelings; of course it is an indie game – and Jayanth, one of the star video game writers of her generation, is perfectly at home here, where a modest budget is the trade-off for making joyful games about colonialism, identity and sexuality, with people whose values align with hers. The money is smaller, and that hurts getting the work noticed.

Harnessing the wide-spread availability of cell phones, many nonprofits have launched mobile health (mHealth) programs to deliver information via voice or text to beneficiaries in underserved communities, with maternal and infant health being a key area of such mHealth programs. Unfortunately, dwindling listenership is a major challenge, requiring targeted interventions using limited resources. This paper focuses on Kilkari, the world's largest mHealth program for maternal and child care - with over 3 million active subscribers at a time - launched by India's Ministry of Health and Family Welfare (MoHFW) and run by the non-profit ARRMAN. We present a system called CHAHAK that aims to reduce automated dropouts as well as boost engagement with the program through the strategic allocation of interventions to beneficiaries. Past work in a similar domain has focused on a much smaller scale mHealth program and used markovian restless multiarmed bandits to optimize a single limited intervention resource. However this paper demonstrates the challenges in adopting a markovian approach in Kilkari; therefore CHAHAK instead relies on non-markovian time-series restless bandits, and optimizes multiple interventions to improve listenership. We use real Kilkari data from the Odisha state in India to show CHAHAK's effectiveness in harnessing multiple interventions to boost listenership, benefiting marginalized communities. When deployed CHAHAK will assist the largest maternal mHealth program to date.

Aspect-Based Sentiment Analysis (ABSA) is increasingly crucial in Natural Language Processing (NLP) for applications such as customer feedback analysis and product recommendation systems. ABSA goes beyond traditional sentiment analysis by extracting sentiments related to specific aspects mentioned in the text; existing attention-based models often need help to effectively connect aspects with context due to language complexity and multiple sentiment polarities in a single sentence. Recent research underscores the value of integrating syntactic information, such as dependency trees, to understand long-range syntactic relationships better and link aspects with context. Despite these advantages, challenges persist, including sensitivity to parsing errors and increased computational complexity when combining syntactic and semantic information. To address these issues, we propose Amplifying Aspect-Sentence Awareness (A3SN), a novel technique designed to enhance ABSA through amplifying aspect-sentence awareness attention. Following the transformer's standard process, our innovative approach incorporates multi-head attention mechanisms to augment the model with sentence and aspect semantic information. We added another multi-head attention module: amplify aspect-sentence awareness attention. By doubling its focus between the sentence and aspect, we effectively highlighted aspect importance within the sentence context. This enables accurate capture of subtle relationships and dependencies. Additionally, gated fusion integrates feature representations from multi-head and amplified aspect-sentence awareness attention mechanisms, which is essential for ABSA. Experimental results across three benchmark datasets demonstrate A3SN's effectiveness and outperform state-of-the-art (SOTA) baseline models.

Machine learning (ML)-based content moderation tools are essential to keep online spaces free from hateful communication. Yet, ML tools can only be as capable as the quality of the data they are trained on allows them. While there is increasing evidence that they underperform in detecting hateful communications directed towards specific identities and may discriminate against them, we know surprisingly little about the provenance of such bias. To fill this gap, we present a systematic review of the datasets for the automated detection of hateful communication introduced over the past decade, and unpack the quality of the datasets in terms of the identities that they embody: those of the targets of hateful communication that the data curators focused on, as well as those unintentionally included in the datasets. We find, overall, a skewed representation of selected target identities and mismatches between the targets that research conceptualizes and ultimately includes in datasets. Yet, by contextualizing these findings in the language and location of origin of the datasets, we highlight a positive trend towards the broadening and diversification of this research space.

The human brain performs tasks with an outstanding energy-efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a lightweight inference scheme specifically designed for DNNs trained using the Forward-Forward algorithm. We have evaluated our proposed lightweight inference scheme in the case of the MNIST and CIFAR datasets, as well as two real-world applications, namely, epileptic seizure detection and cardiac arrhythmia classification using wearable technologies, where complexity overheads/energy consumption is a major constraint, and demonstrate its relevance.

Traditional recommendation proposals, including content-based and collaborative filtering, usually focus on similarity between items or users. Existing approaches lack ways of introducing unexpectedness into recommendations, prioritizing globally popular items over exposing users to unforeseen items. This investigation aims to design and evaluate a novel layer on top of recommender systems suited to incorporate relational information and suggest items with a user-defined degree of surprise. We propose a Knowledge Graph (KG) based recommender system by encoding user interactions on item catalogs. Our study explores whether network-level metrics on KGs can influence the degree of surprise in recommendations. We hypothesize that surprisingness correlates with certain network metrics, treating user profiles as subgraphs within a larger catalog KG. The achieved solution reranks recommendations based on their impact on structural graph metrics. Our research contributes to optimizing recommendations to reflect the metrics. We experimentally evaluate our approach on two datasets of LastFM listening histories and synthetic Netflix viewing profiles. We find that reranking items based on complex network metrics leads to a more unexpected and surprising composition of recommendation lists.