The current method for predicting causal links in knowledge graphs uses weighted causal relations. For a given link between cause-effect entities, the presence of a confounder affects the causal link prediction, which can lead to spurious and inaccurate results. We aim to block these confounders using backdoor path adjustment. Backdoor paths are non-causal association flows that connect the \textit{cause-entity} to the \textit{effect-entity} through other variables. Removing these paths ensures a more accurate prediction of causal links. This paper proposes CausalLPBack, a novel approach to causal link prediction that eliminates backdoor paths and uses knowledge graph link prediction methods. It extends the representation of causality in a neuro-symbolic framework, enabling the adoption and use of traditional causal AI concepts and methods. We demonstrate our approach using a causal reasoning benchmark dataset of simulated videos. The evaluation involves a unique dataset splitting method called the Markov-based split that's relevant for causal link prediction. The evaluation of the proposed approach demonstrates atleast 30\% in MRR and 16\% in Hits@K inflated performance for causal link prediction that is due to the bias introduced by backdoor paths for both baseline and weighted causal relations.

Causal networks are often incomplete with missing causal links. This is due to various issues, such as missing observation data. Recent approaches to the issue of incomplete causal networks have used knowledge graph link prediction methods to find the missing links. In the causal link A causes B causes C, the influence of A to C is influenced by B which is known as a mediator. Existing approaches using knowledge graph link prediction do not consider these mediated causal links. This paper presents HyperCausalLP, an approach designed to find missing causal links within a causal network with the help of mediator links. The problem of missing links is formulated as a hyper-relational knowledge graph completion. The approach uses a knowledge graph link prediction model trained on a hyper-relational knowledge graph with the mediators. The approach is evaluated on a causal benchmark dataset, CLEVRER-Humans. Results show that the inclusion of knowledge about mediators in causal link prediction using hyper-relational knowledge graph improves the performance on an average by 5.94% mean reciprocal rank.

Rare events are occurrences that take place with a significantly lower frequency than more common regular events. In manufacturing, predicting such events is particularly important, as they lead to unplanned downtime, shortening equipment lifespan, and high energy consumption. The occurrence of events is considered frequently-rare if observed in more than 10% of all instances, very-rare if it is 1-5%, moderately-rare if it is 5-10%, and extremely-rare if less than 1%. The rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be highly imbalanced, which leads to bias in predictive models. This paper evaluates the role of data enrichment techniques combined with supervised machine-learning techniques for rare event detection and prediction. To address the data scarcity, we use time series data augmentation and sampling methods to amplify the dataset with more multivariate features and data points while preserving the underlying time series patterns in the combined alterations. Imputation techniques are used in handling null values in datasets. Considering 15 learning models ranging from statistical learning to machine learning to deep learning methods, the best-performing model for the selected datasets is obtained and the efficacy of data enrichment is evaluated. Based on this evaluation, our results find that the enrichment procedure enhances up to 48% of F1 measure in rare failure event detection and prediction of supervised prediction models. We also conduct empirical and ablation experiments on the datasets to derive dataset-specific novel insights. Finally, we investigate the interpretability aspect of models for rare event prediction, considering multiple methods.

Pathfinding problems are found throughout robotics, computational science, and natural sciences. Traditional methods to solve these require training deep neural networks (DNNs) for each new problem domain, consuming substantial time and resources. This study introduces a novel foundation model, leveraging deep reinforcement learning to train heuristic functions that seamlessly adapt to new domains without further fine-tuning. Building upon DeepCubeA, we enhance the model by providing the heuristic function with the domain's state transition information, improving its adaptability. Utilizing a puzzle generator for the 15-puzzle action space variation domains, we demonstrate our model's ability to generalize and solve unseen domains. We achieve a strong correlation between learned and ground truth heuristic values across various domains, as evidenced by robust R-squared and Concordance Correlation Coefficient metrics. These results underscore the potential of foundation models to establish new standards in efficiency and adaptability for AI-driven solutions in complex pathfinding problems.

Automatic citation generation for sentences in a document or report is paramount for intelligence analysts, cybersecurity, news agencies, and education personnel. In this research, we investigate whether large language models (LLMs) are capable of generating references based on two forms of sentence queries: (a) Direct Queries, LLMs are asked to provide author names of the given research article, and (b) Indirect Queries, LLMs are asked to provide the title of a mentioned article when given a sentence from a different article. To demonstrate where LLM stands in this task, we introduce a large dataset called REASONS comprising abstracts of the 12 most popular domains of scientific research on arXiv. From around 20K research articles, we make the following deductions on public and proprietary LLMs: (a) State-of-the-art, often called anthropomorphic GPT-4 and GPT-3.5, suffers from high pass percentage (PP) to minimize the hallucination rate (HR). When tested with Perplexity.ai (7B), they unexpectedly made more errors; (b) Augmenting relevant metadata lowered the PP and gave the lowest HR; (c) Advance retrieval-augmented generation (RAG) using Mistral demonstrates consistent and robust citation support on indirect queries and matched performance to GPT-3.5 and GPT-4. The HR across all domains and models decreased by an average of 41.93%, and the PP was reduced to 0% in most cases. In terms of generation quality, the average F1 Score and BLEU were 68.09% and 57.51%, respectively; (d) Testing with adversarial samples showed that LLMs, including the Advance RAG Mistral, struggle to understand context, but the extent of this issue was small in Mistral and GPT-4-Preview. Our study contributes valuable insights into the reliability of RAG for automated citation generation tasks.

The troubling rise of hallucination presents perhaps the most significant impediment to the advancement of responsible AI. In recent times, considerable research has focused on detecting and mitigating hallucination in Large Language Models (LLMs). However, it's worth noting that hallucination is also quite prevalent in Vision-Language models (VLMs). In this paper, we offer a fine-grained discourse on profiling VLM hallucination based on two tasks: i) image captioning, and ii) Visual Question Answering (VQA). We delineate eight fine-grained orientations of visual hallucination: i) Contextual Guessing, ii) Identity Incongruity, iii) Geographical Erratum, iv) Visual Illusion, v) Gender Anomaly, vi) VLM as Classifier, vii) Wrong Reading, and viii) Numeric Discrepancy. We curate Visual HallucInation eLiciTation (VHILT), a publicly available dataset comprising 2,000 samples generated using eight VLMs across two tasks of captioning and VQA along with human annotations for the categories as mentioned earlier.

Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding, its significance for collaborative agents, and similarities and differences in grounding approaches in both communities. The article examines the potential of neuro-symbolic approaches tailored for grounding tasks, showcasing how they can more comprehensively address grounding. Finally, we discuss areas for further exploration and development in grounding.

The ability of Large Language Models (LLMs) to encode syntactic and semantic structures of language is well examined in NLP. Additionally, analogy identification, in the form of word analogies are extensively studied in the last decade of language modeling literature. In this work we specifically look at how LLMs' abilities to capture sentence analogies (sentences that convey analogous meaning to each other) vary with LLMs' abilities to encode syntactic and semantic structures of sentences. Through our analysis, we find that LLMs' ability to identify sentence analogies is positively correlated with their ability to encode syntactic and semantic structures of sentences. Specifically, we find that the LLMs which capture syntactic structures better, also have higher abilities in identifying sentence analogies.

Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems.

Natural language understanding (NLU) using neural network pipelines often requires additional context that is not solely present in the input data. Through Prior research, it has been evident that NLU benchmarks are susceptible to manipulation by neural models, wherein these models exploit statistical artifacts within the encoded external knowledge to artificially inflate performance metrics for downstream tasks. Our proposed approach, known as the Recap, Deliberate, and Respond (RDR) paradigm, addresses this issue by incorporating three distinct objectives within the neural network pipeline. Firstly, the Recap objective involves paraphrasing the input text using a paraphrasing model in order to summarize and encapsulate its essence. Secondly, the Deliberation objective entails encoding external graph information related to entities mentioned in the input text, utilizing a graph embedding model. Finally, the Respond objective employs a classification head model that utilizes representations from the Recap and Deliberation modules to generate the final prediction. By cascading these three models and minimizing a combined loss, we mitigate the potential for gaming the benchmark and establish a robust method for capturing the underlying semantic patterns, thus enabling accurate predictions. To evaluate the effectiveness of the RDR method, we conduct tests on multiple GLUE benchmark tasks. Our results demonstrate improved performance compared to competitive baselines, with an enhancement of up to 2\% on standard metrics. Furthermore, we analyze the observed evidence for semantic understanding exhibited by RDR models, emphasizing their ability to avoid gaming the benchmark and instead accurately capture the true underlying semantic patterns.