Saskatoon
Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
Zhou, Wei, Mesgar, Mohsen, Friedrich, Annemarie, Adel, Heike
Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular form. Previous approaches demonstrated notable performance by leveraging either closed-source large language models (LLMs) or fine-tuned open-weight LLMs. However, fine-tuning LLMs requires high-quality training data, which is costly to obtain, and utilizing closed-source LLMs poses accessibility challenges and leads to reproducibility issues. In this paper, we propose Multi-Agent Collaboration with Tool use (MACT), a framework that requires neither closed-source models nor fine-tuning. In MACT, a planning agent and a coding agent that also make use of tools collaborate to answer questions. Our experiments on four TQA benchmarks show that MACT outperforms previous SoTA systems on three out of four benchmarks and that it performs comparably to the larger and more expensive closed-source model GPT-4 on two benchmarks, even when using only open-weight models without any fine-tuning. We conduct extensive analyses to prove the effectiveness of MACT's multi-agent collaboration in TQA.
Navigating AI to Unpack Youth Privacy Concerns: An In-Depth Exploration and Systematic Review
Shrestha, Ajay Kumar, Barthwal, Ankur, Campbell, Molly, Shouli, Austin, Syed, Saad, Joshi, Sandhya, Vassileva, Julita
This systematic literature review investigates perceptions, concerns, and expectations of young digital citizens regarding privacy in artificial intelligence (AI) systems, focusing on social media platforms, educational technology, gaming systems, and recommendation algorithms. Using a rigorous methodology, the review started with 2,000 papers, narrowed down to 552 after initial screening, and finally refined to 108 for detailed analysis. Data extraction focused on privacy concerns, data-sharing practices, the balance between privacy and utility, trust factors in AI, transparency expectations, and strategies to enhance user control over personal data. Findings reveal significant privacy concerns among young users, including a perceived lack of control over personal information, potential misuse of data by AI, and fears of data breaches and unauthorized access. These issues are worsened by unclear data collection practices and insufficient transparency in AI applications. The intention to share data is closely associated with perceived benefits and data protection assurances. The study also highlights the role of parental mediation and the need for comprehensive education on data privacy. Balancing privacy and utility in AI applications is crucial, as young digital citizens value personalized services but remain wary of privacy risks. Trust in AI is significantly influenced by transparency, reliability, predictable behavior, and clear communication about data usage. Strategies to improve user control over personal data include access to and correction of data, clear consent mechanisms, and robust data protection assurances. The review identifies research gaps and suggests future directions, such as longitudinal studies, multicultural comparisons, and the development of ethical AI frameworks.
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
Nahid, Md Mahadi Hasan, Rafiei, Davood
Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data. Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation, but they often struggle with large tables due to their limited input length. In this paper, we propose TabSQLify, a novel method that leverages text-to-SQL generation to decompose tables into smaller and relevant sub-tables, containing only essential information for answering questions or verifying statements, before performing the reasoning task. In our comprehensive evaluation on four challenging datasets, our approach demonstrates comparable or superior performance compared to prevailing methods reliant on full tables as input. Moreover, our method can reduce the input context length significantly, making it more scalable and efficient for large-scale table reasoning applications. Our method performs remarkably well on the WikiTQ benchmark, achieving an accuracy of 64.7%. Additionally, on the TabFact benchmark, it achieves a high accuracy of 79.5%. These results surpass other LLM-based baseline models on gpt-3.5-turbo (chatgpt). TabSQLify can reduce the table size significantly alleviating the computational load on LLMs when handling large tables without compromising performance.
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Wang, Zilong, Zhang, Hao, Li, Chun-Liang, Eisenschlos, Julian Martin, Perot, Vincent, Wang, Zifeng, Miculicich, Lesly, Fujii, Yasuhisa, Shang, Jingbo, Lee, Chen-Yu, Pfister, Tomas
Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verification. Compared with generic reasoning, table-based reasoning requires the extraction of underlying semantics from both free-form questions and semi-structured tabular data. Chain-of-Thought and its similar approaches incorporate the reasoning chain in the form of textual context, but it is still an open question how to effectively leverage tabular data in the reasoning chain. Specifically, we guide LLMs using in-context learning to iteratively generate operations and update the table to represent a tabular reasoning chain. LLMs can therefore dynamically plan the next operation based on the results of the previous ones. This continuous evolution of the table forms a chain, showing the reasoning process for a given tabular problem. The chain carries structured information of the intermediate results, enabling more accurate and reliable predictions. Tables are a popular data format and widely used in daily life (Cafarella et al., 2008). Understanding tabular data with language models can benefit various downstream tasks, such as table-based fact verification (Chen et al., 2019), and table-based question answering (Jin et al., 2022). Distinct from pure text, tables deliver rich information through the interaction between rows and columns in the tabular structure, which enhances the data capacity but also increases the difficulty for language models to understand them. Thus, reasoning over the tabular data is an important direction in natural language processing and attracts increasing attention from both academia and industry. In recent years, several approaches have been suggested to tackle the problem of table understanding by training language models. One common direction is to add specialized embedding layers or attention mechanisms into language models and pre-train the models by recovering table cells or segments (Herzig et al., 2020; Wang et al., 2021; Gu et al., 2022; Andrejczuk et al., 2022).
Extending the WILDS Benchmark for Unsupervised Adaptation
Sagawa, Shiori, Koh, Pang Wei, Lee, Tony, Gao, Irena, Xie, Sang Michael, Shen, Kendrick, Kumar, Ananya, Hu, Weihua, Yasunaga, Michihiro, Marklund, Henrik, Beery, Sara, David, Etienne, Stavness, Ian, Guo, Wei, Leskovec, Jure, Saenko, Kate, Hashimoto, Tatsunori, Levine, Sergey, Finn, Chelsea, Liang, Percy
Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data. However, existing distribution shift benchmarks for unlabeled data do not reflect the breadth of scenarios that arise in real-world applications. In this work, we present the WILDS 2.0 update, which extends 8 of the 10 datasets in the WILDS benchmark of distribution shifts to include curated unlabeled data that would be realistically obtainable in deployment. To maintain consistency, the labeled training, validation, and test sets, as well as the evaluation metrics, are exactly the same as in the original WILDS benchmark. These datasets span a wide range of applications (from histology to wildlife conservation), tasks (classification, regression, and detection), and modalities (photos, satellite images, microscope slides, text, molecular graphs). We systematically benchmark state-of-the-art methods that leverage unlabeled data, including domain-invariant, self-training, and self-supervised methods, and show that their success on WILDS 2.0 is limited. To facilitate method development and evaluation, we provide an open-source package that automates data loading and contains all of the model architectures and methods used in this paper. Code and leaderboards are available at https://wilds.stanford.edu.
Multi-Stage Graph Peeling Algorithm for Probabilistic Core Decomposition
Guo, Yang, Zhang, Xuekui, Esfahani, Fatemeh, Srinivasan, Venkatesh, Thomo, Alex, Xing, Li
Mining dense subgraphs where vertices connect closely with each other is a common task when analyzing graphs. A very popular notion in subgraph analysis is core decomposition. Recently, Esfahani et al. presented a probabilistic core decomposition algorithm based on graph peeling and Central Limit Theorem (CLT) that is capable of handling very large graphs. Their proposed peeling algorithm (PA) starts from the lowest degree vertices and recursively deletes these vertices, assigning core numbers, and updating the degree of neighbour vertices until it reached the maximum core. However, in many applications, particularly in biology, more valuable information can be obtained from dense sub-communities and we are not interested in small cores where vertices do not interact much with others. To make the previous PA focus more on dense subgraphs, we propose a multi-stage graph peeling algorithm (M-PA) that has a two-stage data screening procedure added before the previous PA. After removing vertices from the graph based on the user-defined thresholds, we can reduce the graph complexity largely and without affecting the vertices in subgraphs that we are interested in. We show that M-PA is more efficient than the previous PA and with the properly set filtering threshold, can produce very similar if not identical dense subgraphs to the previous PA (in terms of graph density and clustering coefficient).
21-year-old Saskatoon man making waves in artificial intelligence
Over the summer, Landon Garrison, a 21-year-old computer science major, spent roughly 12 hours each day writing the code for a website he's just launched called clevrML. The website offers easier solutions for people looking to build artificial intelligence based programs. "(I wanted) to make the process of making these artificial intelligence models easier, and simpler, without having to write any code," Garrison said. "For the code that you do have to write, if you do want to, for developers, it's very simple, very straightforward, and pre-made. He saw what he believed to be a hole in the market, for an easier, more affordable way to offer A.I. "In A.I. right now there's a trend of model sizes and computation going up, and I figure for most people it needs to go down and be more affordable for everybody," he said.
Canadian farmers slow to warm to AI, automation
Standing onstage in an ornate conference room at the Delta Bessborough Hotel in downtown Saskatoon, former Saskatchewan premier Dr. Grant Devine pitched the agri-food industry on a new idea: a wheat tube. More specifically, a hypothetical hyperloop Devine says could fire shipments of wheat from Moose Jaw to Langley, B.C. at hundreds of kilometres an hour. He says students at the University of Saskatchewan, where he is a professor, had priced the idea at around $18 billion. "You'd load it like you would any other hopper car, load it in the capsule and -- zoom! -- it's out there in a matter of hours," Devine said. Dr. Grant Devine speaks at the AIC2019 conference in Saskatoon, SK on Wednesday, November 6, 2019.