Recent work has suggested that end-to-end system designs for cross-lingual summarization are competitive solutions that perform on par or even better than traditional pipelined designs. A closer look at the evidence reveals that this intuition is based on the results of only a handful of languages or using underpowered pipeline baselines. In this work, we compare these two paradigms for cross-lingual summarization on 39 source languages into English and show that a simple \textit{translate-then-summarize} pipeline design consistently outperforms even an end-to-end system with access to enormous amounts of parallel data. For languages where our pipeline model does not perform well, we show that system performance is highly correlated with publicly distributed BLEU scores, allowing practitioners to establish the feasibility of a language pair a priori. Contrary to recent publication trends, our result suggests that the combination of individual progress of monolingual summarization and translation tasks offers better performance than an end-to-end system, suggesting that end-to-end designs should be considered with care.

Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing software in terms of user numbers in human history and become an important foundational model for the next generation of artificial intelligence applications. However, the generations of LLMs are not entirely reliable, often producing content with factual errors, biases, and toxicity. Given their vast number of users and wide range of application scenarios, these unreliable responses can lead to many serious negative impacts. This thesis introduces the exploratory works in the field of language model reliability during the PhD study, focusing on the correctness, non-toxicity, and fairness of LLMs from both software testing and natural language processing perspectives. First, to measure the correctness of LLMs, we introduce two testing frameworks, FactChecker and LogicAsker, to evaluate factual knowledge and logical reasoning accuracy, respectively. Second, for the non-toxicity of LLMs, we introduce two works for red-teaming LLMs. Third, to evaluate the fairness of LLMs, we introduce two evaluation frameworks, BiasAsker and XCulturalBench, to measure the social bias and cultural bias of LLMs, respectively.

The digitization of historical documents is crucial for preserving the cultural heritage of the society. An important step in this process is converting scanned images to text using Optical Character Recognition (OCR), which can enable further search, information extraction, etc. Unfortunately, this is a hard problem as standard OCR tools are not tailored to deal with historical orthography as well as with challenging layouts. Thus, it is standard to apply an additional text correction step on the OCR output when dealing with such documents. In this work, we focus on Bulgarian, and we create the first benchmark dataset for evaluating the OCR text correction for historical Bulgarian documents written in the first standardized Bulgarian orthography: the Drinov orthography from the 19th century. We further develop a method for automatically generating synthetic data in this orthography, as well as in the subsequent Ivanchev orthography, by leveraging vast amounts of contemporary literature Bulgarian texts. We then use state-of-the-art LLMs and encoder-decoder framework which we augment with diagonal attention loss and copy and coverage mechanisms to improve the post-OCR text correction. The proposed method reduces the errors introduced during recognition and improves the quality of the documents by 25\%, which is an increase of 16\% compared to the state-of-the-art on the ICDAR 2019 Bulgarian dataset. We release our data and code at \url{https://github.com/angelbeshirov/post-ocr-text-correction}.}

In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances efficiency and performance in fine-tuning large models by reducing the number of trainable parameters and computational costs. However, current advancements in LoRA might be focused on its fine-tuning methodologies, with not as much exploration as might be expected into further compression of LoRA. Since most of LoRA's parameters might still be superfluous, this may lead to unnecessary wastage of computational resources. In this paper, we propose \textbf{CoRA}: leveraging shared knowledge to optimize LoRA training by substituting its matrix $B$ with a common subspace from large models. Our two-fold method includes (1) Freezing the substitute matrix $B$ to halve parameters while training matrix $A$ for specific tasks and (2) Using the substitute matrix $B$ as an enhanced initial state for the original matrix $B$, achieving improved results with the same parameters. Our experiments show that the first approach achieves the same efficacy as the original LoRA fine-tuning while being more efficient than halving parameters. At the same time, the second approach has some improvements compared to LoRA's original fine-tuning performance. They generally attest to the effectiveness of our work.

Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of defense mechanisms and explore model vulnerabilities. These methods can uncover and exploit weaknesses in models, promoting the development of more robust architectures. However, current methods for transferable attacks often come with substantial computational costs, limiting their deployment and application, especially in edge computing scenarios. Adversarial generative models, such as Generative Adversarial Networks (GANs), are characterized by their ability to generate samples without the need for retraining after an initial training phase. GE-AdvGAN, a recent method for transferable adversarial attacks, is based on this principle. In this paper, we propose a novel general framework for gradient editing-based transferable attacks, named GE-AdvGAN+, which integrates nearly all mainstream attack methods to enhance transferability while significantly reducing computational resource consumption. Our experiments demonstrate the compatibility and effectiveness of our framework. Compared to the baseline AdvGAN, our best-performing method, GE-AdvGAN++, achieves an average ASR improvement of 47.8. Additionally, it surpasses the latest competing algorithm, GE-AdvGAN, with an average ASR increase of 5.9. The framework also exhibits enhanced computational efficiency, achieving 2217.7 FPS, outperforming traditional methods such as BIM and MI-FGSM. The implementation code for our GE-AdvGAN+ framework is available at https://github.com/GEAdvGANP

As Artificial Intelligence (AI) becomes integral to business operations, integrating Responsible AI (RAI) within Environmental, Social, and Governance (ESG) frameworks is essential for ethical and sustainable AI deployment. This study examines how leading companies align RAI with their ESG goals. Through interviews with 28 industry leaders, we identified a strong link between RAI and ESG practices. However, a significant gap exists between internal RAI policies and public disclosures, highlighting the need for greater board-level expertise, robust governance, and employee engagement. We provide key recommendations to strengthen RAI strategies, focusing on transparency, cross-functional collaboration, and seamless integration into existing ESG frameworks.

The digitisation of historical print media archives is crucial for increasing accessibility to contemporary records. However, the process of Optical Character Recognition (OCR) used to convert physical records to digital text is prone to errors, particularly in the case of newspapers and periodicals due to their complex layouts. This paper introduces Context Leveraging OCR Correction (CLOCR-C), which utilises the infilling and context-adaptive abilities of transformer-based language models (LMs) to improve OCR quality. The study aims to determine if LMs can perform post-OCR correction, improve downstream NLP tasks, and the value of providing the socio-cultural context as part of the correction process. Experiments were conducted using seven LMs on three datasets: the 19th Century Serials Edition (NCSE) and two datasets from the Overproof collection. The results demonstrate that some LMs can significantly reduce error rates, with the top-performing model achieving over a 60% reduction in character error rate on the NCSE dataset. The OCR improvements extend to downstream tasks, such as Named Entity Recognition, with increased Cosine Named Entity Similarity. Furthermore, the study shows that providing socio-cultural context in the prompts improves performance, while misleading prompts lower performance. In addition to the findings, this study releases a dataset of 91 transcribed articles from the NCSE, containing a total of 40 thousand words, to support further research in this area. The findings suggest that CLOCR-C is a promising approach for enhancing the quality of existing digital archives by leveraging the socio-cultural information embedded in the LMs and the text requiring correction.

Traditional benchmarking in NLP typically involves using static held-out test sets. However, this approach often results in an overestimation of performance and lacks the ability to offer comprehensive, interpretable, and dynamic assessments of NLP models. Recently, works like DynaBench (Kiela et al., 2021) and CheckList (Ribeiro et al., 2020) have addressed these limitations through behavioral testing of NLP models with test types generated by a multistep human-annotated pipeline. Unfortunately, manually creating a variety of test types requires much human labor, often at prohibitive cost. In this work, we propose SYNTHEVAL, a hybrid behavioral testing framework that leverages large language models (LLMs) to generate a wide range of test types for a comprehensive evaluation of NLP models. SYNTHEVAL first generates sentences via LLMs using controlled generation, and then identifies challenging examples by comparing the predictions made by LLMs with task-specific NLP models. In the last stage, human experts investigate the challenging examples, manually design templates, and identify the types of failures the taskspecific models consistently exhibit. We apply SYNTHEVAL to two classification tasks, sentiment analysis and toxic language detection, and show that our framework is effective in identifying weaknesses of strong models on these tasks. We share our code in https://github.com/Loreley99/SynthEval_CheckList.

As information retrieval systems continue to evolve, accurate evaluation and benchmarking of these systems become pivotal. Web search datasets, such as MS MARCO, primarily provide short keyword queries without accompanying intent or descriptions, posing a challenge in comprehending the underlying information need. This paper proposes an approach to augmenting such datasets to annotate informative query descriptions, with a focus on two prominent benchmark datasets: TREC-DL-21 and TREC-DL-22. Our methodology involves utilizing state-of-the-art LLMs to analyze and comprehend the implicit intent within individual queries from benchmark datasets. By extracting key semantic elements, we construct detailed and contextually rich descriptions for these queries. To validate the generated query descriptions, we employ crowdsourcing as a reliable means of obtaining diverse human perspectives on the accuracy and informativeness of the descriptions. This information can be used as an evaluation set for tasks such as ranking, query rewriting, or others.

To track the performance of emerging models and understand their capabilities, the research community has developed We report initial work towards constructing ecologically valid a variety of benchmarks for video-and embodied-question answering benchmarks to assess the capabilities of large multimodal models [7, 9, 11, 12, 14, 20, 22]. These benchmarks are typically for engaging in situated collaboration. In contrast to existing constructed by identifying a preexisting multimodal dataset (or benchmarks, in which question-answer pairs are generated post creating a synthetic one via a virtual environment), and then generating hoc over preexisting or synthetic datasets via templates, human question-answer pairs from templates, human annotators, or annotators, or large language models (LLMs), we propose and investigate via LLMs. The questions are designed to probe model capabilities an interactive system-driven approach, where the questions along various dimensions, such as spatial understanding, episodic are generated by users in context, during their interactions with memory, and the recognition of objects and their attributes. While an end-to-end situated AI system. We illustrate how the questions these benchmarks provide useful probes for model competency, we that arise are different in form and content from questions typically argue that they do not accurately capture the types of questions found in existing embodied question answering (EQA) benchmarks users ask when engaged in a real-time task, and thus do not reflect and discuss new real-world challenge problems brought to the fore.