Related papers: Towards General-Purpose Data Discovery: A Programm…

Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal…

Deep learning models for natural language processing rely heavily on high-quality labeled datasets. However, existing labeling approaches often struggle to balance label quality with labeling cost. To address this challenge, we propose…

Recently, integrating external tools with Large Language Models (LLMs) has gained significant attention as an effective strategy to mitigate the limitations inherent in their pre-training data. However, real-world systems often incorporate…

Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does not belong to -- are provided to the learning algorithm.…

Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we…

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users…

We propose the vision of a functional data model (FDM) and an associated functional query language (FQL). Our proposal has far-reaching consequences: we show a path to come up with a modern QL that solves (almost if not) all problems of SQL…

Our aim is to investigate ontology-based data access over temporal data with validity time and ontologies capable of temporal conceptual modelling. To this end, we design a temporal description logic, TQL, that extends the standard ontology…

Knowledge Tracing (KT) is a critical component in online learning, but traditional approaches face limitations in interpretability and cross-domain adaptability. This paper introduces Language Model-based Code Knowledge Tracing (CodeLKT),…

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming…

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events,…

In recent years, groundbreaking advancements in natural language processing have culminated in the emergence of powerful large language models (LLMs), which have showcased remarkable capabilities across a vast array of domains, including…

In-context learning using large language models has recently shown surprising results for semantic parsing tasks such as Text-to-SQL translation. Prompting GPT-3 or Codex using several examples of question-SQL pairs can produce excellent…

Analytics on structured data is a mature field with many successful methods. However, most real world data exists in unstructured form, such as images and conversations. We investigate the potential of Large Language Models (LLMs) to enable…

Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning, which is crucial for tasks such as table question answering (TQA) and table-based fact verification (TFV).…

Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs. However, most of the existing methods heavily rely on domain experts, require excessive computational cost, or…

How to generate a large, realistic set of tables along with joinability relationships, to stress-test dataset discovery methods? Dataset discovery methods aim to automatically identify related data assets in a data lake. The development and…

The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…

Developing the capacity to effectively search for requisite datasets is an urgent requirement to assist data users in identifying relevant datasets considering the very limited available metadata. For this challenge, the utilization of…

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…