Related papers: LeoPARD --- A Generic Platform for the Implementat…

Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available. However, deep learning solely focuses on the accuracy of the predictions, neglecting the reasoning process…

Complex dialog systems often use retrieved evidence to facilitate factual responses. Such RAG (Retrieval Augmented Generation) systems retrieve from massive heterogeneous data stores that are usually architected as multiple indexes or APIs…

Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdisciplinary research. Recently, various LLM-based agents have been developed to assist scientific…

Logic programs with ordered disjunction (LPODs) combine ideas underlying Qualitative Choice Logic (Brewka et al. KR 2002) and answer set programming. Logic programming under answer set semantics is extended with a new connective called…

This paper presents Ellogon, a multi-lingual, cross-platform, general-purpose text engineering environment. Ellogon was designed in order to aid both researchers in natural language processing, as well as companies that produce language…

We provide a computational definition of the notions of vector space and bilinear functions. We use this result to introduce a minimal language combining higher-order computation and linear algebra. This language extends the Lambda-calculus…

Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid external knowledge, such as unstructured text and structured…

We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation. Our architecture is trained end-to-end…

Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases. Towards this goal, there is a notable shift to building compound AI systems,…

Large Language Models (LLMs) are versatile, yet they often falter in tasks requiring deep and reliable reasoning due to issues like hallucinations, limiting their applicability in critical scenarios. This paper introduces a rigorously…

Semantic parsing is a means of taking natural language and putting it in a form that a computer can understand. There has been a multitude of approaches that take natural language utterances and form them into lambda calculus expressions --…

The paper presents our system developed for table question answering (TQA). TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address…

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Despite the remarkable advancements and widespread applications of deep neural networks, their ability to perform reasoning tasks remains limited, particularly in domains requiring structured, abstract thought. In this paper, we investigate…

In most current research, large language models (LLMs) are able to perform reasoning tasks by generating chains of thought through the guidance of specific prompts. However, there still exists a significant discrepancy between their…

The ability of neural networks to represent more features than neurons makes interpreting them challenging. This phenomenon, known as superposition, has spurred efforts to find architectures that are more interpretable than standard…

We introduce the MultiLang Code Parser Dataset (MLCPD), a large-scale, language-agnostic dataset unifying syntactic and structural representations of code across ten major programming languages. MLCPD contains over seven million parsed…

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…

Memory is identified as a crucial human faculty that allows for the retention of visual and linguistic information within the hippocampus and neurons in the brain, which can subsequently be retrieved to address real-world challenges that…