Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. LLMs are typically evaluated using accuracy, yet this metric does not capture the vulnerability of LLMs to hallucination-inducing factors like prompt and context variability. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? In this paper, we propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability. MONITOR computes the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts.Experiments on a comprehensive range of 12 LLMs demonstrate the effectiveness of MONITOR in evaluating the factual reliability of LLMs while maintaining a low computational overhead. In addition, we release the FKTC (Factual Knowledge Test Corpus) test set, containing 210,158 prompts in total to foster research along this line (https://github.com/Vicky-Wil/MONITOR).

In this study, a gait phase classification method based on SVM multiclass classification is introduced, with a focus on the precise identification of the stance and swing phases, which are further subdivided into seven phases. Data from individual IMU sensors, such as Shank Acceleration X, Y, Z, Shank Gyro X, and Knee Angles, are used as features in this classification model. The suggested technique successfully classifies the various gait phases with a significant accuracy of about 90.3%. Gait phase classification is crucial, especially in the domains of exoskeletons and prosthetics, where accurate identification of gait phases enables seamless integration with assistive equipment, improving mobility, stability, and energy economy. This study extends the study of gait and offers an effective method for correctly identifying gait phases from Shank IMU sensor data, with potential applications in biomechanical research, exoskeletons, rehabilitation, and prosthetics.

Infectious disease outbreaks continue to pose a significant threat to human health and well-being. To improve disease surveillance and understanding of disease spread, several surveillance systems have been developed to monitor daily news alerts and social media. However, existing systems lack thorough epidemiological analysis in relation to corresponding alerts or news, largely due to the scarcity of well-annotated reports data. To address this gap, we introduce the Biomedical Alert News Dataset (BAND), which includes 1,508 samples from existing reported news articles, open emails, and alerts, as well as 30 epidemiology-related questions. These questions necessitate the model's expert reasoning abilities, thereby offering valuable insights into the outbreak of the disease. The BAND dataset brings new challenges to the NLP world, requiring better disguise capability of the content and the ability to infer important information. We provide several benchmark tasks, including Named Entity Recognition (NER), Question Answering (QA), and Event Extraction (EE), to show how existing models are capable of handling these tasks in the epidemiology domain. To the best of our knowledge, the BAND corpus is the largest corpus of well-annotated biomedical outbreak alert news with elaborately designed questions, making it a valuable resource for epidemiologists and NLP researchers alike.

Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user's hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (\textit{Cue}-CoT), which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue, aiming to provide a more personalized and engaging response. To evaluate the approach, we build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English, targeting 3 major linguistic cues during the conversation: \textit{personality}, \textit{emotion}, and \textit{psychology}. We conduct extensive experiments on the proposed benchmark with 5 LLMs under both zero-shot and one-shot settings. Empirical results demonstrate our proposed \textit{Cue}-CoT method outperforms standard prompting methods in terms of both \textit{helpfulness} and \textit{acceptability} on all datasets.

Multi-hop logical reasoning over knowledge graph (KG) plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding (CQE) methods for reasoning focus on static KGs, while temporal knowledge graphs (TKGs) have not been fully explored. Reasoning over TKGs has two challenges: 1. The query should answer entities or timestamps; 2. The operators should consider both set logic on entity set and temporal logic on timestamp set. To bridge this gap, we define the multi-hop logical reasoning problem on TKGs. With generated three datasets, we propose the first temporal CQE named Temporal Feature-Logic Embedding framework (TFLEX) to answer the temporal complex queries. We utilize vector logic to compute the logic part of Temporal Feature-Logic embeddings, thus naturally modeling all First-Order Logic (FOL) operations on entity set. In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between). Experiments on numerous query patterns demonstrate the effectiveness of our method.

The recent developments in soft computing cannot be complete without noting the contributions of artificial neural machine learning systems that draw inspiration from real cortical tissue or processes that occur in human brain. The universal approximability of such neural systems has led to its wide spread use, and novel developments in this evolving technology has shown that there is a bright future for such Artificial Intelligent (AI) techniques in the soft computing field. Indeed, the proliferation of large and very deep networks of artificial neural systems and the corresponding enhancement and development of neural machine learning algorithms have contributed immensely to the development of the modern field of Deep Learning as may be found in the well documented research works of Lecun, Bengio and Hinton. However, the key requirements of end user affordability in addition to reduced complexity and reduced data learning size requirement means there still remains a need for the synthesis of more cost-efficient and less data-hungry artificial neural systems. In this report, we present an overview of a new competing bio-inspired continual learning neural tool Neuronal Auditory Machine Intelligence (Neuro-AMI) as a predictor detailing its functional and structural details, important aspects on right applicability, some recent application use cases and future research directions for current and prospective machine learning experts and data scientists.

In this paper, we share our best performing submission to the Arabic AI Tasks Evaluation Challenge (ArAIEval) at ArabicNLP 2023. Our focus was on Task 1, which involves identifying persuasion techniques in excerpts from tweets and news articles. The persuasion technique in Arabic texts was detected using a training loop with XLM-RoBERTa, a language-agnostic text representation model. This approach proved to be potent, leveraging fine-tuning of a multilingual language model. In our evaluation of the test set, we achieved a micro F1 score of 0.64 for subtask A of the competition.

Addressing the gap in understanding visual comprehension in Large Language Models (LLMs), we designed a challenge-response study, subjecting Google Bard and GPT-Vision to 64 visual tasks, spanning categories like "Visual Situational Reasoning" and "Next Scene Prediction." Previous models, such as GPT4, leaned heavily on optical character recognition tools like Tesseract, whereas Bard and GPT-Vision, akin to Google Lens and Visual API, employ deep learning techniques for visual text recognition. However, our findings spotlight both vision-language model's limitations: while proficient in solving visual CAPTCHAs that stump ChatGPT alone, it falters in recreating visual elements like ASCII art or analyzing Tic Tac Toe grids, suggesting an over-reliance on educated visual guesses. The prediction problem based on visual inputs appears particularly challenging with no common-sense guesses for next-scene forecasting based on current "next-token" multimodal models. This study provides experimental insights into the current capacities and areas for improvement in multimodal LLMs.

Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability. Despite its wide adoption, we empirically show that prompt-tuning is vulnerable to downstream task-agnostic backdoors, which reside in the pretrained models and can affect arbitrary downstream tasks. The state-of-the-art backdoor detection approaches cannot defend against task-agnostic backdoors since they hardly converge in reversing the backdoor triggers. To address this issue, we propose LMSanitator, a novel approach for detecting and removing task-agnostic backdoors on Transformer models. Instead of directly inverting the triggers, LMSanitator aims to invert the predefined attack vectors (pretrained models' output when the input is embedded with triggers) of the task-agnostic backdoors, which achieves much better convergence performance and backdoor detection accuracy. LMSanitator further leverages prompt-tuning's property of freezing the pretrained model to perform accurate and fast output monitoring and input purging during the inference phase. Extensive experiments on multiple language models and NLP tasks illustrate the effectiveness of LMSanitator. For instance, LMSanitator achieves 92.8% backdoor detection accuracy on 960 models and decreases the attack success rate to less than 1% in most scenarios.

Combining large language models with logical reasoning enhance their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges to gathering reliable data from web for building comprehensive training datasets, subsequently affecting the performance on downstream tasks. To address this, we introduce a novel logic-driven data augmentation approach, AMR-LDA. AMR-LDA converts the original text into an Abstract Meaning Representation (AMR) graph, a structured semantic representation that encapsulates the logic structure of the sentence, upon which operations are performed to generate logically modified AMR graphs. The modified AMR graphs are subsequently converted back into texts to create augmented data. Notably, our methodology is architecture-agnostic and enhances generative large language models, such as GPT-3.5 and GPT-4, through prompt augmentation, and fine-tuning discriminative large language models through contrastive learning with logic-driven data augmentation. Empirical evidence underscores the efficacy of our proposed method with improvement in performance across seven downstream tasks, such as logical reasoning reading comprehension, textual entailment, and natural language inference. Furthermore, our method ranked first on the ReClor leaderboard \url{https://eval.ai/web/challenges/challenge-page/503/leaderboard/1347}. The source code and data are publicly available \url{https://github.com/Strong-AI-Lab/Logical-Equivalence-driven-AMR-Data-Augmentation-for-Representation-Learning}.