Large Language Models (LLMs) have ushered in a new era in Natural Language Processing, but their massive size demands effective compression techniques for practicality. Although numerous model compression techniques have been investigated, they typically rely on a calibration set that overlooks the multilingual context and results in significant accuracy degradation for low-resource languages. This paper introduces Multilingual Brain Surgeon (MBS), a novel calibration data sampling method for multilingual LLMs compression. MBS overcomes the English-centric limitations of existing methods by sampling calibration data from various languages proportionally to the language distribution of the model training datasets. Our experiments, conducted on the BLOOM multilingual LLM, demonstrate that MBS improves the performance of existing English-centric compression methods, especially for low-resource languages. We also uncover the dynamics of language interaction during compression, revealing that the larger the proportion of a language in the training set and the more similar the language is to the calibration language, the better performance the language retains after compression. In conclusion, MBS presents an innovative approach to compressing multilingual LLMs, addressing the performance disparities and improving the language inclusivity of existing compression techniques.

Scientific articles play a crucial role in advancing knowledge and informing research directions. One key aspect of evaluating scientific articles is the analysis of citations, which provides insights into the impact and reception of the cited works. This article introduces the innovative use of large language models, particularly ChatGPT, for comprehensive sentiment analysis of citations within scientific articles. By leveraging advanced natural language processing (NLP) techniques, ChatGPT can discern the nuanced positivity or negativity of citations, offering insights into the reception and impact of cited works. Furthermore, ChatGPT's capabilities extend to detecting potential biases and conflicts of interest in citations, enhancing the objectivity and reliability of scientific literature evaluation. This study showcases the transformative potential of artificial intelligence (AI)-powered tools in enhancing citation analysis and promoting integrity in scholarly research.

This paper presents different neural network-based classifier algorithms for diagnosing and classifying Anemia. The study compares these classifiers with established models such as Feed Forward Neural Network (FFNN), Elman network, and Non-linear Auto-Regressive Exogenous model (NARX). Experimental evaluations were conducted using data from clinical laboratory test results for 230 patients. The proposed neural network features nine inputs (age, gender, RBC, HGB, HCT, MCV, MCH, MCHC, WBCs) and one output. The simulation outcomes for diverse patients demonstrate that the suggested artificial neural network rapidly and accurately detects the presence of the disease. Consequently, the network could be seamlessly integrated into clinical laboratories for automatic generation of Anemia patients' reports Additionally, the suggested method is affordable and can be deployed on hardware at low costs.

Compression techniques have been crucial in advancing machine learning by enabling efficient training and deployment of large-scale language models. However, these techniques have received limited attention in the context of low-resource language models, which are trained on even smaller amounts of data and under computational constraints, a scenario known as the "low-resource double-bind." This paper investigates the effectiveness of pruning, knowledge distillation, and quantization on an exclusively low-resourced, small-data language model, AfriBERTa. Through a battery of experiments, we assess the effects of compression on performance across several metrics beyond accuracy. Our study provides evidence that compression techniques significantly improve the efficiency and effectiveness of small-data language models, confirming that the prevailing beliefs regarding the effects of compression on large, heavily parameterized models hold true for less-parameterized, small-data models.

Existing discourse corpora are annotated based on different frameworks, which show significant dissimilarities in definitions of arguments and relations and structural constraints. Despite surface differences, these frameworks share basic understandings of discourse relations. The relationship between these frameworks has been an open research question, especially the correlation between relation inventories utilized in different frameworks. Better understanding of this question is helpful for integrating discourse theories and enabling interoperability of discourse corpora annotated under different frameworks. However, studies that explore correlations between discourse relation inventories are hindered by different criteria of discourse segmentation, and expert knowledge and manual examination are typically needed. Some semi-automatic methods have been proposed, but they rely on corpora annotated in multiple frameworks in parallel. In this paper, we introduce a fully automatic approach to address the challenges. Specifically, we extend the label-anchored contrastive learning method introduced by Zhang et al. (2022b) to learn label embeddings during a classification task. These embeddings are then utilized to map discourse relations from different frameworks. We show experimental results on RST-DT (Carlson et al., 2001) and PDTB 3.0 (Prasad et al., 2018).

Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements. In response, we propose PoLLMgraph, a Polygraph for LLMs, as an effective model-based white-box detection and forecasting approach. PoLLMgraph distinctly differs from the large body of existing research that concentrates on addressing such challenges through black-box evaluations. In particular, we demonstrate that hallucination can be effectively detected by analyzing the LLM's internal state transition dynamics during generation via tractable probabilistic models. Experimental results on various open-source LLMs confirm the efficacy of PoLLMgraph, outperforming state-of-the-art methods by a considerable margin, evidenced by over 20% improvement in AUC-ROC on common benchmarking datasets like TruthfulQA. Our work paves a new way for model-based white-box analysis of LLMs, motivating the research community to further explore, understand, and refine the intricate dynamics of LLM behaviors.

Despite their strong ability to retrieve knowledge in English, current large language models show imbalance abilities in different languages. Two approaches are proposed to address this, i.e., multilingual pretraining and multilingual instruction tuning. However, whether and how do such methods contribute to the cross-lingual knowledge alignment inside the models is unknown. In this paper, we propose CLiKA, a systematic framework to assess the cross-lingual knowledge alignment of LLMs in the Performance, Consistency and Conductivity levels, and explored the effect of multilingual pretraining and instruction tuning on the degree of alignment. Results show that: while both multilingual pretraining and instruction tuning are beneficial for cross-lingual knowledge alignment, the training strategy needs to be carefully designed. Namely, continued pretraining improves the alignment of the target language at the cost of other languages, while mixed pretraining affect other languages less. Also, the overall cross-lingual knowledge alignment, especially in the conductivity level, is unsatisfactory for all tested LLMs, and neither multilingual pretraining nor instruction tuning can substantially improve the cross-lingual knowledge conductivity.

Fox News chief national security correspondent Jennifer Griffin reports on how autonomous weapons used in Ukraine have transformed the battlefield on'Special Report.' A series of scandals has blighted Denmark's Armed Forces at a time when the Scandinavian country and member of the NATO alliance is building up its defenses, chiefly as a response to Russia's invasion of Ukraine. The events have so far led to the dismissal this week of Denmark's top military chief, Gen. Flemming Lentfer, who failed to inform the defense minister about an incident on the frigate HDMS Iver Huitfeldt last month while deployed to the Red Sea, where it was part of a U.S.-led operation to defend commercial shipping against Houthi militants. On Thursday, a technical error onboard its sister ship, the frigate HDMS Niels Juel that was docked in a Danish harbor, led to the air space and maritime route being briefly closed due to fears a navy missile might launch unintentionally -- but not explode -- and send fragments falling into the busy shipping lane between the islands of Zeeland, where Copenhagen sits, and Funen. The Iver Huitfeldt, which returned from its Red Sea mission on Thursday, ahead of schedule, reportedly experienced a half-hour long malfunction of its missile and radar systems during a drone attack on March 9, according to the specialist defense news website Olfi.

The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia. These datasets cover documents like invoices and receipts with sparse annotations such that they support one or two co-related tasks (e.g., entity extraction and entity linking). Unfortunately, only focusing on a single specific of documents or task is not representative of how documents often need to be processed in the wild - where variety in style and requirements is expected. In this paper, we introduce BuDDIE (Business Document Dataset for Information Extraction), the first multi-task dataset of 1,665 real-world business documents that contains rich and dense annotations for DC, KEE, and VQA. Our dataset consists of publicly available business entity documents from US state government websites. The documents are structured and vary in their style and layout across states and types (e.g., forms, certificates, reports, etc.). We provide data variety and quality metrics for BuDDIE as well as a series of baselines for each task. Our baselines cover traditional textual, multi-modal, and large language model approaches to VRDU.

People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life. However, practice environments for social skills are typically out of reach for most people. How can we make social skill training more available, accessible, and inviting? Drawing upon interdisciplinary research from communication and psychology, this perspective paper identifies social skill barriers to enter specialized fields. Then we present a solution that leverages large language models for social skill training via a generic framework. Our AI Partner, AI Mentor framework merges experiential learning with realistic practice and tailored feedback. This work ultimately calls for cross-disciplinary innovation to address the broader implications for workforce development and social equality.