Summary of Can Ai Extract Antecedent Factors Of Human Trust in Ai? An Application Of Information Extraction For Scientific Literature in Behavioural and Computer Sciences, by Melanie Mcgrath et al.
Can AI Extract Antecedent Factors of Human Trust in AI? An Application of Information Extraction for Scientific Literature in Behavioural and Computer Sciences
by Melanie McGrath, Harrison Bailey, Necva Bölücü, Xiang Dai, Sarvnaz Karimi, Cecile Paris
First submitted to arxiv on: 16 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper investigates the relationships between factors contributing to human trust in artificial intelligence applications, specifically focusing on information extraction techniques. By designing annotation guidelines with domain experts and creating an annotated English dataset, the study aims to explore the complex space of Trust in AI. The researchers use large language models (LLMs) for named entity and relation extraction, benchmarking their results against state-of-the-art methods. Their findings suggest that supervised learning is necessary, which may not be feasible with prompt-based LLMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how humans trust artificial intelligence applications. It’s a complex problem because there are many factors that can affect trust. The researchers created a dataset of labeled text to help them understand these relationships better. They used large language models to extract specific information from the text, like named entities and relationships. Their results show that they need supervised learning to solve this problem, which might not be possible with current technology. |
Keywords
» Artificial intelligence » Prompt » Supervised
