High quality summarization data remains scarce in under-represented languages. However, historical newspapers, made available through recent digitization efforts, offer an abundant source of untapped, naturally annotated data. In this work, we present a novel method for collecting naturally occurring summaries via Front-Page Teasers, where editors summarize full length articles. We show that this phenomenon is common across seven diverse languages and supports multi-document summarization. To scale data collection, we develop an automatic process, suited to varying linguistic resource levels. Finally, we apply this process to a Hebrew newspaper title, producing HEBTEASESUM, the first dedicated multi-document summarization dataset in Hebrew.

Emotions that somebody develops based on an argument do not only depend on the argument itself - they are also influenced by a subjective evaluation of the argument's potential impact on the self. For instance, an argument to ban plastic bottles might cause fear of losing a job for a bottle industry worker, which lowers the convincingness - presumably independent of its content. While binary emotionality of arguments has been studied, such cognitive appraisal models have only been proposed in other subtasks of emotion analysis, but not in the context of arguments and their convincingness. To fill this research gap, we propose the Contextualized Argument Appraisal Framework to model the interplay between the sender, receiver, and argument. We adapt established appraisal models from psychology to argument mining, including argument pleasantness, familiarity, response urgency, and expected effort, as well as convincingness variables. To evaluate the framework and pave the way for computational modeling, we develop a novel role-playing-based annotation setup, mimicking real-world exposure to arguments. Participants disclose their emotion, explain the main cause, the argument appraisal, and the perceived convincingness. To consider the subjective nature of such annotations, we also collect demographic data and personality traits of both the participants and ask them to disclose the same variables for their perception of the argument sender. The analysis of the resulting ContArgA corpus of 4000 annotations reveals that convincingness is positively correlated with positive emotions (e.g., trust) and negatively correlated with negative emotions (e.g., anger). The appraisal variables particularly point to the importance of the annotator's familiarity with the argument.

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has shown how the robustness of de-identification methods could be assessed by attempting the reverse process of _re-identification_, based on an automated adversary using its background knowledge to uncover the PIIs that have been masked. This paper presents two complementary strategies to build stronger re-identification attacks. We first show that (1) the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results. We also find that (2) reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.

While de-identification models can help conceal the identity of the individual(s) mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-identified text back to its source. One straightforward way to perform such linkages is to extract phrases from the de-identified document and then check their presence in the original dataset. This paper presents a method to counter search-based linkage attacks while preserving the semantic integrity of the text. The method proceeds in two steps. We first construct an inverted index of the N-grams occurring in the document collection, making it possible to efficiently determine which N-grams appear in less than $k$ documents (either alone or in combination with other N-grams). An LLM-based rewriter is then iteratively queried to reformulate those spans until linkage is no longer possible. Experimental results on a collection of court cases show that the method is able to effectively prevent search-based linkages while remaining faithful to the original content.

--T alent identification plays a critical role in promoting student development. However, traditional approaches often rely on manual processes or focus narrowly on academic achievement, and typically delaying intervention until the higher education stage. This oversight overlooks diverse non-academic talents and misses opportunities for early intervention. T o address this gap, this study introduces T alentPredictor, a novel semi-supervised multi-modal neural network that combines Transformer, LSTM, and ANN architectures. This model is designed to predict seven different talent types--academic, sport, art, leadership, service, technology, and others--in secondary school students within an offline educational setting. Drawing on existing offline educational data from 1,041 local secondary students, T alentPredictor overcomes the limitations of traditional talent identification methods. By clustering various award records into talent categories and extracting features from students' diverse learning behaviors, it achieves high prediction accuracy (0.908 classification accuracy, 0.908 ROCAUC). This demonstrates the potential of machine learning to identify diverse talents early in student development. ALENT is a critical component in human society. It is indispensable to the development of societies and the competitiveness of countries. Last but not least, talent is always in high demand. Thus, nurturing talent is the top priority for every part of the earth, and in it, talent identification is the foundation, as you must have a target individual to nurture talent. Traditional talent identification aims to give students tests that exceed their current level. For example, give grade eight students college admissions tests and use the result of the tough test as a talent score.

Neanderthals bred with our human ancestors 100,000 years earlier than previously thought, according to a new study. Experts have discovered that a five–year–old child who lived 140,000 years ago had parents from both species. Their fossil – likely a female – was first unearthed 90 years ago in the Skhul Cave on Mount Carmel in what is now northern Israel. A team from Tel Aviv University and the French Centre for Scientific Research conducted a series of advanced tests on the remaining bones, including a CT scan of the skull. 'Genetic studies over the past decade have shown that these two groups exchanged genes,' said lead author Professor Israel Hershkovitz.

In assessing argument strength, the notions of what makes a good argument are manifold. With the broader trend towards treating subjectivity as an asset and not a problem in NLP, new dimensions of argument quality are studied. Although studies on individual subjective features like personal stories exist, there is a lack of large-scale analyses of the relation between these features and argument strength. To address this gap, we conduct regression analysis to quantify the impact of subjective factors $-$ emotions, storytelling, and hedging $-$ on two standard datasets annotated for objective argument quality and subjective persuasion. As such, our contribution is twofold: at the level of contributed resources, as there are no datasets annotated with all studied dimensions, this work compares and evaluates automated annotation methods for each subjective feature. At the level of novel insights, our regression analysis uncovers different patterns of impact of subjective features on the two facets of argument strength encoded in the datasets. Our results show that storytelling and hedging have contrasting effects on objective and subjective argument quality, while the influence of emotions depends on their rhetoric utilization rather than the domain.

The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating real-world design workflows due to their designs' simplicity, inadequate design specifications, and less rigorous verification environments. To address these limitations, we present RealBench, the first benchmark aiming at real-world IP-level Verilog generation tasks. RealBench features complex, structured, real-world open-source IP designs, multi-modal and formatted design specifications, and rigorous verification environments, including 100% line coverage testbenches and a formal checker. It supports both module-level and system-level tasks, enabling comprehensive assessments of LLM capabilities. Evaluations on various LLMs and agents reveal that even one of the best-performing LLMs, o1-preview, achieves only a 13.3% pass@1 on module-level tasks and 0% on system-level tasks, highlighting the need for stronger Verilog generation models in the future. The benchmark is open-sourced at https://github.com/IPRC-DIP/RealBench.

Despite the rapid progress in the capabilities of Large Language Models (LLMs), they continue to have difficulty following relatively simple, unambiguous instructions, especially when compositions are involved. In this paper, we take inspiration from recent work that suggests that models may follow instructions better when they are expressed in pseudo-code. However, writing pseudo-code programs can be tedious and using few-shot demonstrations to craft code representations for use in inference can be unnatural for non-expert users of LLMs. To overcome these limitations, we propose fine-tuning LLMs with instruction-tuning data that additionally includes instructions re-expressed in pseudo-code along with the final response. We evaluate models trained using our method on $11$ publicly available benchmarks comprising of tasks related to instruction-following, mathematics, and common-sense reasoning. We conduct rigorous experiments with $5$ different models and find that not only do models follow instructions better when trained with pseudo-code, they also retain their capabilities on the other tasks related to mathematical and common sense reasoning. Specifically, we observe a relative gain of $3$--$19$% on instruction-following benchmark, and an average gain of upto 14% across all tasks.

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for estimating model capabilities, they often fail to establish true upper bounds or predict deployment behavior. This literature review consolidates the rapidly evolving field of AI safety evaluations, proposing a systematic taxonomy around three dimensions: what properties we measure, how we measure them, and how these measurements integrate into frameworks. We show how evaluations go beyond benchmarks by measuring what models can do when pushed to the limit (capabilities), the behavioral tendencies exhibited by default (propensities), and whether our safety measures remain effective even when faced with subversive adversarial AI (control). These properties are measured through behavioral techniques like scaffolding, red teaming and supervised fine-tuning, alongside internal techniques such as representation analysis and mechanistic interpretability. We provide deeper explanations of some safety-critical capabilities like cybersecurity exploitation, deception, autonomous replication, and situational awareness, alongside concerning propensities like power-seeking and scheming. The review explores how these evaluation methods integrate into governance frameworks to translate results into concrete development decisions. We also highlight challenges to safety evaluations - proving absence of capabilities, potential model sandbagging, and incentives for "safetywashing" - while identifying promising research directions. By synthesizing scattered resources, this literature review aims to provide a central reference point for understanding AI safety evaluations.