Related papers: Commonsense Reasoning and Large Network Analysis: …

Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages. Existing resources impose a trade-off: structured knowledge bases lack textual grounding,…

We lay the foundations for a database-inspired approach to interpreting and understanding neural network models by querying them using declarative languages. Towards this end we study different query languages, based on first-order logic,…

Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words,…

Recently, pretrained language models (e.g., BERT) have achieved great success on many downstream natural language understanding tasks and exhibit a certain level of commonsense reasoning ability. However, their performance on commonsense…

With the future striving toward data-centric decision-making, seamless access to databases is of utmost importance. There is extensive research on creating an efficient text-to-sql (TEXT2SQL) model to access data from the database. Using a…

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature, a capability that remains challenging for both retrieval-based systems and unconstrained language models. While recent work has…

Network interpretation as an effort to reveal the features learned by a network remains largely visualization-based. In this paper, our goal is to tackle semantic network interpretation at both filter and decision level. For filter-level…

In complex, high dimensional and unstructured data it is often difficult to extract meaningful patterns. This is especially the case when dealing with textual data. Recent studies in machine learning, information theory and network science…

Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must first acquire…

Relevant information in documents is often summarized in tables, helping the reader to identify useful facts. Most benchmark datasets support either document layout analysis or table understanding, but lack in providing data to apply both…

We propose a novel framework to facilitate the on-demand design of data-centric systems by exploiting domain knowledge from an existing ontology. Its key ingredient is a process that we call focusing, which allows to obtain a schema for a…

Progress on commonsense reasoning is usually measured from performance improvements on Question Answering tasks designed to require commonsense knowledge. However, fine-tuning large Language Models (LMs) on these specific tasks does not…

A sememe is defined as the minimum semantic unit of human languages. Sememe knowledge bases (KBs), which contain words annotated with sememes, have been successfully applied to many NLP tasks, and we believe that by learning the smallest…

Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge. We believe the main reason is the lack of commonsense \mbox{connections}…

In recent years, a new interest for the use of graph-theory based networks has emerged within the field of cognitive science. This has played a key role in mining the large amount of data generated by word association norms. In the present…

We present a submission to the CogALex 2016 shared task on the corpus-based identification of semantic relations, using LexNET (Shwartz and Dagan, 2016), an integrated path-based and distributional method for semantic relation…

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Analyzing a distributed computation is a hard problem in general due to the combinatorial explosion in the size of the state-space with the number of processes in the system. By abstracting the computation, unnecessary explorations can be…

Classification, which involves finding rules that partition a given data set into disjoint groups, is one class of data mining problems. Approaches proposed so far for mining classification rules for large databases are mainly decision tree…