Conventional automated test generation tools struggle to generate test oracles and tricky bug-revealing test inputs. Large Language Models (LLMs) can be prompted to produce test inputs and oracles for a program directly, but the precision of the tests can be very low for complex scenarios (only 6.3% based on our experiments). To fill this gap, this paper proposes AID, which combines LLMs with differential testing to generate fault-revealing test inputs and oracles targeting plausibly correct programs (i.e., programs that have passed all the existing tests). In particular, AID selects test inputs that yield diverse outputs on a set of program variants generated by LLMs, then constructs the test oracle based on the outputs. We evaluate AID on two large-scale datasets with tricky bugs: TrickyBugs and EvalPlus, and compare it with three state-of-the-art baselines. The evaluation results show that the recall, precision, and F1 score of AID outperform the state-of-the-art by up to 1.80x, 2.65x, and 1.66x, respectively.

Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates that each client labels their data for training, which can be both time-consuming and resource-intensive, and may even be impractical for edge devices. Moreover, the training and transmission of deep models present challenges to the computation and communication capabilities of the clients. To address these two inherent challenges in supervised federated learning, we propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication by harnessing pretrained vision-language models, such as CLIP. By capitalizing on the zero-shot prediction capability and the well-trained image encoder of the pre-trained CLIP model, we have carefully crafted an efficient and resilient self-training approach. This method refines the initial zero-shot predicted pseudo-labels of unlabeled instances through the sole training of a linear classifier on top of the fixed image encoder. Additionally, to address data heterogeneity within each client, we propose a class-balanced text feature sampling strategy for generating synthetic instances in the feature space to support local training. Experiments are conducted on multiple benchmark datasets. The experimental results demonstrate that our proposed method greatly enhances model performance in comparison to CLIP's zero-shot predictions and even outperforms supervised federated learning benchmark methods given limited computational and communication overhead.

Ontology alignment, a critical process in the Semantic Web for detecting relationships between different ontologies, has traditionally focused on identifying so-called "simple" 1-to-1 relationships through class labels and properties comparison. The more practically useful exploration of more complex alignments remains a hard problem to automate, and as such is largely underexplored, i.e. in application practice it is usually done manually by ontology and domain experts. Recently, the surge in Natural Language Processing (NLP) capabilities, driven by advancements in Large Language Models (LLMs), presents new opportunities for enhancing ontology engineering practices, including ontology alignment tasks. This paper investigates the application of LLM technologies to tackle the complex ontology alignment challenge. Leveraging a prompt-based approach and integrating rich ontology content - so-called modules - our work constitutes a significant advance towards automating the complex alignment task.

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it has recently been shown that the increase in models' capabilities has enabled LLMs to make accurate privacy-infringing inferences from previously unseen texts. With the rise of multimodal vision-language models (VLMs), capable of understanding both images and text, a pertinent question is whether such results transfer to the previously unexplored domain of benign images posted online. To investigate the risks associated with the image reasoning capabilities of newly emerging VLMs, we compile an image dataset with human-annotated labels of the image owner's personal attributes. In order to understand the additional privacy risk posed by VLMs beyond traditional human attribute recognition, our dataset consists of images where the inferable private attributes do not stem from direct depictions of humans. On this dataset, we evaluate the inferential capabilities of 7 state-of-the-art VLMs, finding that they can infer various personal attributes at up to 77.6% accuracy. Concerningly, we observe that accuracy scales with the general capabilities of the models, implying that future models can be misused as stronger adversaries, establishing an imperative for the development of adequate defenses.

Large language models (LLMs), such as GPT3.5, GPT4 and LLAMA2 perform surprisingly well and outperform human experts on many tasks. However, in many domain-specific evaluations, these LLMs often suffer from hallucination problems due to insufficient training of relevant corpus. Furthermore, fine-tuning large models may face problems such as the LLMs are not open source or the construction of high-quality domain instruction is difficult. Therefore, structured knowledge databases such as knowledge graph can better provide domain background knowledge for LLMs and make full use of the reasoning and analysis capabilities of LLMs. In some previous works, LLM was called multiple times to determine whether the current triplet was suitable for inclusion in the subgraph when retrieving subgraphs through a question. Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power. Moreover, when choosing the reasoning path, LLM will be called once for each step, and if one of the steps is selected incorrectly, it will lead to the accumulation of errors in the following steps. In this paper, we integrated and optimized a pipeline for selecting reasoning paths from KG based on LLM, which can reduce the dependency on LLM. In addition, we propose a simple and effective subgraph retrieval method based on chain of thought (CoT) and page rank which can returns the paths most likely to contain the answer. We conduct experiments on three datasets: GenMedGPT-5k [14], WebQuestions [2], and CMCQA [21]. Finally, RoK can demonstrate that using fewer LLM calls can achieve the same results as previous SOTAs models.

Large language models (LLMs) are now widely used in various fields, including finance. However, Japanese financial-specific LLMs have not been proposed yet. Hence, this study aims to construct a Japanese financial-specific LLM through continual pre-training. Before tuning, we constructed Japanese financial-focused datasets for continual pre-training. As a base model, we employed a Japanese LLM that achieved state-of-the-art performance on Japanese financial benchmarks among the 10-billion-class parameter models. After continual pre-training using the datasets and the base model, the tuned model performed better than the original model on the Japanese financial benchmarks. Moreover, the outputs comparison results reveal that the tuned model's outputs tend to be better than the original model's outputs in terms of the quality and length of the answers. These findings indicate that domain-specific continual pre-training is also effective for LLMs. The tuned model is publicly available on Hugging Face.

Socioeconomic bias in society exacerbates disparities, influencing access to opportunities and resources based on individuals' economic and social backgrounds. This pervasive issue perpetuates systemic inequalities, hindering the pursuit of inclusive progress as a society. In this paper, we investigate the presence of socioeconomic bias, if any, in large language models. To this end, we introduce a novel dataset SilverSpoon, consisting of 3000 samples that illustrate hypothetical scenarios that involve underprivileged people performing ethically ambiguous actions due to their circumstances, and ask whether the action is ethically justified. Further, this dataset has a dual-labeling scheme and has been annotated by people belonging to both ends of the socioeconomic spectrum. Using SilverSpoon, we evaluate the degree of socioeconomic bias expressed in large language models and the variation of this degree as a function of model size. We also perform qualitative analysis to analyze the nature of this bias. Our analysis reveals that while humans disagree on which situations require empathy toward the underprivileged, most large language models are unable to empathize with the socioeconomically underprivileged regardless of the situation. To foster further research in this domain, we make SilverSpoon and our evaluation harness publicly available.

Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a plethora of complex tasks that require a fundamental understanding of human language. Given that these embeddings themselves often reflect or exhibit bias, it stands to reason that these models may also inadvertently learn this bias. In this work, we build on the seminal previous work and propose DeepSoftDebias, an algorithm that uses a neural network to perform 'soft debiasing'. We exhaustively evaluate this algorithm across a variety of SOTA datasets, accuracy metrics, and challenging NLP tasks. We find that DeepSoftDebias outperforms the current state-of-the-art methods at reducing bias across gender, race, and religion.

Generative Artificial Intelligence (GAI) models such as ChatGPT have experienced a surge in popularity, attracting 100 million active users in 2 months and generating an estimated 10 million daily queries. Despite this remarkable adoption, there remains a limited understanding to which extent this innovative technology influences higher education. This research paper investigates the impact of GAI on university students and Higher Education Institutions (HEIs). The study adopts a mixed-methods approach, combining a comprehensive survey with scenario analysis to explore potential benefits, drawbacks, and transformative changes the new technology brings. Using an online survey with 130 participants we assessed students' perspectives and attitudes concerning present ChatGPT usage in academics. Results show that students use the current technology for tasks like assignment writing and exam preparation and believe it to be a effective help in achieving academic goals. The scenario analysis afterwards projected potential future scenarios, providing valuable insights into the possibilities and challenges associated with incorporating GAI into higher education. The main motivation is to gain a tangible and precise understanding of the potential consequences for HEIs and to provide guidance responding to the evolving learning environment. The findings indicate that irresponsible and excessive use of the technology could result in significant challenges. Hence, HEIs must develop stringent policies, reevaluate learning objectives, upskill their lecturers, adjust the curriculum and reconsider examination approaches.

Recent advancements of large language models (LLMs) have resulted in indistinguishable text outputs comparable to human-generated text. Watermarking algorithms are potential tools that offer a way to differentiate between LLM- and human-generated text by embedding detectable signatures within LLM-generated output. However, current watermarking schemes lack robustness against known attacks against watermarking algorithms. In addition, they are impractical considering an LLM generates tens of thousands of text outputs per day and the watermarking algorithm needs to memorize each output it generates for the detection to work. In this work, focusing on the limitations of current watermarking schemes, we propose the concept of a "topic-based watermarking algorithm" for LLMs. The proposed algorithm determines how to generate tokens for the watermarked LLM output based on extracted topics of an input prompt or the output of a non-watermarked LLM. Inspired from previous work, we propose using a pair of lists (that are generated based on the specified extracted topic(s)) that specify certain tokens to be included or excluded while generating the watermarked output of the LLM. Using the proposed watermarking algorithm, we show the practicality of a watermark detection algorithm. Furthermore, we discuss a wide range of attacks that can emerge against watermarking algorithms for LLMs and the benefit of the proposed watermarking scheme for the feasibility of modeling a potential attacker considering its benefit vs. loss.