One domain of interest is their use in algorithmic hiring, specifically in matching resumes with job categories. Yet, this introduces issues of bias on protected attributes like gender, race and maternity status. The seminal work of Bertrand & Mullainathan (2003) set the gold-standard for identifying hiring bias via field experiments where the response rate for identical resumes that differ only in protected attributes, e.g., racially suggestive names such as Emily or Lakisha, is compared. We replicate this experiment on state-of-art LLMs (GPT-3.5, Bard, Claude and Llama) to evaluate bias (or lack thereof) on gender, race, maternity status, pregnancy status, and political affiliation. We evaluate LLMs on two tasks: (1) matching resumes to job categories; and (2) summarizing resumes with employment relevant information. Overall, LLMs are robust across race and gender. They differ in their performance on pregnancy status and political affiliation. We use contrastive input decoding on open-source LLMs to uncover potential sources of bias.

We present a multi-scale predictive coding model for future video frames prediction. Drawing inspiration on the ``Predictive Coding" theories in cognitive science, it is updated by a combination of bottom-up and top-down information flows, which can enhance the interaction between different network levels. However, traditional predictive coding models only predict what is happening hierarchically rather than predicting the future. To address the problem, our model employs a multi-scale approach (Coarse to Fine), where the higher level neurons generate coarser predictions (lower resolution), while the lower level generate finer predictions (higher resolution). In terms of network architecture, we directly incorporate the encoder-decoder network within the LSTM module and share the final encoded high-level semantic information across different network levels. This enables comprehensive interaction between the current input and the historical states of LSTM compared with the traditional Encoder-LSTM-Decoder architecture, thus learning more believable temporal and spatial dependencies. Furthermore, to tackle the instability in adversarial training and mitigate the accumulation of prediction errors in long-term prediction, we propose several improvements to the training strategy. Our approach achieves good performance on datasets such as KTH, Moving MNIST and Caltech Pedestrian. Code is available at https://github.com/Ling-CF/MSPN.

The legal domain is a vast and complex field that involves a considerable amount of text analysis, including laws, legal arguments, and legal opinions. Legal practitioners must analyze these texts to understand legal cases, research legal precedents, and prepare legal documents. The size of legal opinions continues to grow, making it increasingly challenging to develop a model that can accurately predict the rhetorical roles of legal opinions given their complexity and diversity. In this research paper, we propose a novel model architecture for automatically predicting rhetorical roles using pre-trained language models (PLMs) enhanced with knowledge of sentence position information within a document. Based on an annotated corpus from the LegalEval@SemEval2023 competition, we demonstrate that our approach requires fewer parameters, resulting in lower computational costs when compared to complex architectures employing a hierarchical model in a global-context, yet it achieves great performance. Moreover, we show that adding more attention to a hierarchical model based only on BERT in the local-context, along with incorporating sentence position information, enhances the results.

Hate speech detection refers to the task of detecting hateful content that aims at denigrating an individual or a group based on their religion, gender, sexual orientation, or other characteristics. Due to the different policies of the platforms, different groups of people express hate in different ways. Furthermore, due to the lack of labeled data in some platforms it becomes challenging to build hate speech detection models. To this end, we revisit if we can learn a generalizable hate speech detection model for the cross platform setting, where we train the model on the data from one (source) platform and generalize the model across multiple (target) platforms. Existing generalization models rely on linguistic cues or auxiliary information, making them biased towards certain tags or certain kinds of words (e.g., abusive words) on the source platform and thus not applicable to the target platforms. Inspired by social and psychological theories, we endeavor to explore if there exist inherent causal cues that can be leveraged to learn generalizable representations for detecting hate speech across these distribution shifts. To this end, we propose a causality-guided framework, PEACE, that identifies and leverages two intrinsic causal cues omnipresent in hateful content: the overall sentiment and the aggression in the text. We conduct extensive experiments across multiple platforms (representing the distribution shift) showing if causal cues can help cross-platform generalization.

Overview This document describes a pragmatic approach on how to migrate enterprise computer systems to new systems that could evolve forever, address the whole organisations and that are integrated. Governance aspects are as important, if not more, than purely technical IT aspects: human resources, supply chains, call for tenders, and similar. Migration implies not starting from a green field. Style of this document {Principle} Lie if it helps and restate the obvious. Enterprise IT architecture is a complex field. Efforts have been made to make this document accessible to the widest possible public, including non-IT people. To make concepts more accessible, they might be introduced informally without being technically strict (lie) and sprinkled with bits of tutorials (restate). For the gory details follow the references. It could be anything: from one integrated system to many disconnected systems, from properly developed systems to spreadsheets, from internal developed code to external libraries, etc. The first priority is to ensure the functioning of the current system, imperfect as it might be. Avoid the syndrome of not maintaining the current system because it is a waste of money. It is an error to channel most of the IT resources into the new wonderful system on the way. The first step is to prepare emergency manuals for the current system. The guiding scenario for preparing these manuals is that present IT staff operating/maintaining the current system disappear from one day to the next; unpolished manuals would do. New IT replacement staff without any previous knowledge should have a sporting chance of operating/maintaining the current system with the help of emergency manuals which must be printed and stored in a place easy to find.

This paper presents a comprehensive review of the current state of the art in quantum navigation systems, with a specific focus on their application in maritime navigation. Quantum technologies have the potential to revolutionise navigation and positioning systems due to their ability to provide highly accurate and secure information. The review covers the principles of quantum navigation and highlights the latest developments in quantum-enhanced sensors, atomic clocks, and quantum communication protocols. The paper also discusses the challenges and opportunities of using quantum technologies in maritime navigation, including the effects that the maritime environment and the specificity of marine applications can have on the performance of quantum sensors. Finally, the paper concludes with a discussion on the future of quantum navigation systems and their potential impact on the maritime industry. This review aims at providing a valuable resource for researchers and engineers interested in the development and deployment of quantum navigation systems.

The US warned the European Union that its proposed law to regulate artificial intelligence would favor companies with the resources to cover the costs of compliance while hurting smaller firms, according to previously undisclosed documents. The US analysis focuses mostly on the European Parliament version of the AI Act, which includes rules on generative AI. Some rules in the parliament law are based on terms that are "vague or undefined," according to the documents, which were obtained by Bloomberg News. The analysis is Washington's most detailed position on the EU legislation that could set the tone for other countries writing rules for AI. One US concern is that the European Parliament focuses on how AI models are developed, whereas the US would prefer an approach that focuses on the risk involved in how these models are actually used.

Robin Williams' daughter, Zelda, spoke out amid the actors strike about her father's voice being used by AI without his consent as experts weigh in on the technology's use in Hollywood.

Observations from dynamical systems often exhibit irregularities, such as censoring, where values are recorded only if they fall within a certain range. Censoring is ubiquitous in practice, due to saturating sensors, limit-of-detection effects, and image-frame effects. In light of recent developments on learning linear dynamical systems (LDSs), and on censored statistics with independent data, we revisit the decades-old problem of learning an LDS, from censored observations (Lee and Maddala (1985); Zeger and Brookmeyer (1986)). Here, the learner observes the state $x_t \in \mathbb{R}^d$ if and only if $x_t$ belongs to some set $S_t \subseteq \mathbb{R}^d$. We develop the first computationally and statistically efficient algorithm for learning the system, assuming only oracle access to the sets $S_t$. Our algorithm, Stochastic Online Newton with Switching Gradients, is a novel second-order method that builds on the Online Newton Step (ONS) of Hazan et al. (2007). Our Switching-Gradient scheme does not always use (stochastic) gradients of the function we want to optimize, which we call "censor-aware" function. Instead, in each iteration, it performs a simple test to decide whether to use the censor-aware, or another "censor-oblivious" function, for getting a stochastic gradient. In our analysis, we consider a "generic" Online Newton method, which uses arbitrary vectors instead of gradients, and we prove an error-bound for it. This can be used to appropriately design these vectors, leading to our Switching-Gradient scheme. This framework significantly deviates from the recent long line of works on censored statistics (e.g., Daskalakis et al. (2018); Kontonis et al. (2019); Daskalakis et al. (2019)), which apply Stochastic Gradient Descent (SGD), and their analysis reduces to establishing conditions for off-the-shelf SGD-bounds.

This work combines algorithms based on word embeddings, dimensionality reduction, and clustering. The objective is to obtain topics from a set of unclassified texts. The algorithm to obtain the word embeddings is the BERT model, a neural network architecture widely used in NLP tasks. Due to the high dimensionality, a dimensionality reduction technique called UMAP is used. This method manages to reduce the dimensions while preserving part of the local and global information of the original data. K-Means is used as the clustering algorithm to obtain the topics. Then, the topics are evaluated using the TF-IDF statistics, Topic Diversity, and Topic Coherence to get the meaning of the words on the clusters. The results of the process show good values, so the topic modeling of this process is a viable option for classifying or clustering texts without labels.