Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, mathematical reasoning, and data mining capabilities. Recent advancements in natural language processing (NLP), particularly with the advent of large language models (LLMs), have introduced promising opportunities for traditional causal inference tasks. This paper reviews recent progress in applying LLMs to causal inference, encompassing various tasks spanning different levels of causation. We summarize the main causal problems and approaches, and present a comparison of their evaluation results in different causal scenarios. Furthermore, we discuss key findings and outline directions for future research, underscoring the potential implications of integrating LLMs in advancing causal inference methodologies.

Anomaly detection on graphs plays an important role in many real-world applications. Usually, these data are composed of multiple types (e.g., user information and transaction records for financial data), thus exhibiting view heterogeneity. Therefore, it can be challenging to leverage such multi-view information and learn the graph's contextual information to identify rare anomalies. To tackle this problem, many deep learning-based methods utilize contrastive learning loss as a regularization term to learn good representations. However, many existing contrastive-based methods show that traditional contrastive learning losses fail to consider the semantic information (e.g., class membership information). In addition, we theoretically show that clustering-based contrastive learning also easily leads to a sub-optimal solution. To address these issues, in this paper, we proposed an autoencoder-based clustering framework regularized by a similarity-guided contrastive loss to detect anomalous nodes. Specifically, we build a similarity map to help the model learn robust representations without imposing a hard margin constraint between the positive and negative pairs. Theoretically, we show that the proposed similarity-guided loss is a variant of contrastive learning loss, and how it alleviates the issue of unreliable pseudo-labels with the connection to graph spectral clustering. Experimental results on several datasets demonstrate the effectiveness and efficiency of our proposed framework.

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.

Abnormal event detection or anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without supervision. In this work we propose an unsupervised approach for video anomaly detection with the aim to jointly optimize the objectives of the deep neural network and the anomaly detection task using a hybrid architecture. Initially, a convolutional autoencoder is pre-trained in an unsupervised manner with a fusion of depth, motion and appearance features. In the second step, we utilize the encoder part of the pre-trained autoencoder and extract the embeddings of the fused input. Now, we jointly train/ fine tune the encoder to map the embeddings to a hypercenter. Thus, embeddings of normal data fall near the hypercenter, whereas embeddings of anomalous data fall far away from the hypercenter.

Labelled data are limited and self-supervised learning is one of the most important approaches for reducing labelling requirements. While it has been extensively explored in the image domain, it has so far not received the same amount of attention in the acoustic domain. Yet, reducing labelling is a key requirement for many acoustic applications. Specifically in bioacoustic, there are rarely sufficient labels for fully supervised learning available. This has led to the widespread use of acoustic recognisers that have been pre-trained on unrelated data for bioacoustic tasks. We posit that training on the actual task data and combining self-supervised pre-training with few-shot classification is a superior approach that has the ability to deliver high accuracy even when only a few labels are available. To this end, we introduce and evaluate a new architecture that combines CNN-based preprocessing with feature extraction based on state space models (SSMs). This combination is motivated by the fact that CNN-based networks alone struggle to capture temporal information effectively, which is crucial for classifying acoustic signals. SSMs, specifically S4 and Mamba, on the other hand, have been shown to have an excellent ability to capture long-range dependencies in sequence data. We pre-train this architecture using contrastive learning on the actual task data and subsequent fine-tuning with an extremely small amount of labelled data. We evaluate the performance of this proposed architecture for ($n$-shot, $n$-class) classification on standard benchmarks as well as real-world data. Our evaluation shows that it outperforms state-of-the-art architectures on the few-shot classification problem.

INTRODUCTION The explosive growth of space technologies that are furthering the information age continue to elicit transformative advances that can chiefly be attributed largely to the inexpensive and reusable commercial launch capabilities. They form a basis for the space technology of the future, which include on-orbit servicing, assembling and manufacturing. Next generation space robotics technologies that focus on particular mechanisms and machines that are suitable for operations in micro and nano gravity environments form an important aspect of research. The confluence of advanced manufacturing technologies, novel materials, electronics and advanced computing architectures forms a fertile precursor for this research. One of the most versatile set of space mechanisms that can be a potential enabler are free-flying systems. Advances in CubeSat technology have continued to further the technology maturation of the free-flyer concept. Ground robotic platforms that focus on CubeSat technology enable accessible and low-cost spacecraft motion emulation solutions that contrast industrial and defense standards. The Land, Air, and Space Robotics (LASR) Laboratory at Texas A&M University has made significant contributions in the areas of dynamics, control and simulation of a Mobile Robotic System for 6-DOF Motion Emulation. The laboratory is home to a variety of robotic platforms that emulate satellite motions. One key robotic testbed is the Holonomic Omnidirectional Motion Emulation Robot (HOMER) that not only replaces air bearing tables for robotic proximity operation testing, but offers realistic 6-DOF motions to test sensors and actuators. The LASR Laboratory is now investigating the use of free-flying spacecraft modules in several different on-orbit, servicing and manufacturing (OSAM) activities as part of the Space University Research Initiative (SURI) funding opportunity awarded by the Air Force Office of Scientific Research to the "Breaking the'Launch Once, Use Once' Paradigm" Team, which consists of Carnegie Mellon University (CMU), University of New Mexico (UNM), Texas A&M University (TAMU), and the Northrop Grumman Corporation (NGC).

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at \url{https://github.com/shrimonmuke0202/AlpaPICO.git}.

In evaluating the long-context capabilities of large language models (LLMs), benchmarks such as "Needle-in-a-Haystack" (NIAH), Ruler, and Needlebench are commonly used. While these benchmarks measure how well models understand longcontext input sequences, they do not effectively gauge the quality of long-form text generation--a critical aspect for applications such as design proposals and creative writing. To address this gap, we have introduced a new long-form text evaluation benchmark, LongGenBench, which tests models' ability to identify specific events within generated long text sequences. In this benchmark, we prompt long-context LMs to create long-form text that must include particular events or constraints and evaluate their ability to incorporate these elements. We evaluated ten longcontext LMs across four distinct scenarios, three types of prompt instructions, and two different generation-length settings (16K and 32K). Although these models perform well on NIAH benchmarks, none demonstrated satisfactory performance on the LongGenBench, raising concerns about their ability to generate coherent long-form text that follows instructions. Recent advances in large language models (LLMs) have significantly enhanced their ability to process and generate long text sequences, which is essential for various natural language processing tasks (Xiong et al., 2023; Bai et al., 2023a). For instance, GPT-4 (Achiam et al., 2023) and LLaMa-3.1 (Dubey et al., 2024) manage context windows of up to 128K tokens; Claude 2.1 (Anthropic, 2024a) supports up to 200K tokens; and the Claude 3 series (Anthropic, 2024b) handles inputs exceeding 1 million tokens.

Stance detection is a crucial NLP task with numerous applications in social science, from analyzing online discussions to assessing political campaigns. This paper investigates the optimal way to incorporate metadata into a political stance detection task. We demonstrate that previous methods combining metadata with language-based data for political stance detection have not fully utilized the metadata information; our simple baseline, using only party membership information, surpasses the current state-of-the-art. We then show that prepending metadata (e.g., party and policy) to political speeches performs best, outperforming all baselines, indicating that complex metadata inclusion systems may not learn the task optimally.

Artificial Intelligence (AI) has revolutionized food marketing by providing advanced techniques for personalized recommendations, consumer behavior prediction, and campaign optimization. This paper explores the shift from traditional advertising methods, such as TV, radio, and print, to AI-driven strategies. Traditional approaches were successful in building brand awareness but lacked the level of personalization that modern consumers demand. AI leverages data from consumer purchase histories, browsing behaviors, and social media activity to create highly tailored marketing campaigns. These strategies allow for more accurate product recommendations, prediction of consumer needs, and ultimately improve customer satisfaction and user experience. AI enhances marketing efforts by automating labor-intensive processes, leading to greater efficiency and cost savings. It also enables the continuous adaptation of marketing messages, ensuring they remain relevant and engaging over time. While AI presents significant benefits in terms of personalization and efficiency, it also comes with challenges, particularly the substantial investment required for technology and skilled expertise. This paper compares the strengths and weaknesses of traditional and AI-driven food marketing techniques, offering valuable insights into how marketers can leverage AI to create more effective and targeted marketing strategies in the evolving digital landscape.