Search for: All records

Recent advances in Large Language Models (LLMs) show the potential to significantly augment or even replace complex human writing activities. However, for complex tasks where people need to make decisions as well as write a justification, the trade offs between making work efficient and hindering decisions remain unclear. In this paper, we explore this question in the context of designing intelligent scaffolding for writing meta-reviews for an academic peer review process. We prototyped a system called MetaWriter'' trained on five years of open peer review data to support meta-reviewing. The system highlights common topics in the original peer reviews, extracts key points by each reviewer, and on request, provides a preliminary draft of a meta-review that can be further edited. To understand how novice and experienced meta-reviewers use MetaWriter, we conducted a within-subject study with 32 participants. Each participant wrote meta-reviews for two papers: one with and one without MetaWriter. We found that MetaWriter significantly expedited the authoring process and improved the coverage of meta-reviews, as rated by experts, compared to the baseline. While participants recognized the efficiency benefits, they raised concerns around trust, over-reliance, and agency. We also interviewed six paper authors to understand their opinions of using machine intelligence to support the peer review process and reported critical reflections. We discuss implications for future interactive AI writing tools to support complex synthesis work. 

Low back pain poses a significant societal burden, with progressive intervertebral disc degeneration (IDD) emerging as a pivotal contributor to chronic pain. Improved animal models of progressive IDD are needed to comprehensively investigate new diagnostic and therapeutic approaches to managing IDD. Recent studies underscore the immune system’s involvement in IDD, particularly with regards to the role of immune privileged tissues such as the nucleus pulposus (NP) becoming an immune targeting following initial disc injury. We therefore hypothesized that generating an active immune response against NP antigens with an NP vaccine could significantly accelerate and refine an IDD animal model triggered by mechanical puncture of the disc. To address this question, rabbits were immunized against NP antigens following disc puncture, and the impact on development of progressive IDD was assessed radiographically, functionally, and histologically compared between vaccinated and non-vaccinated animals over a 12-week period. Immune responses to NP antigens were assessed by ELISA and Western blot. We found that the vaccine elicited strong immune responses against NP antigens, including a dominant ~37 kD antigen. Histologic evaluation revealed increases IDD in animals that received the NP vaccine plus disc puncture, compared to disc puncture and vaccine only animals. Imaging evaluation evidenced a decrease in disc height index and higher scores of disc degeneration in animals after disc punctures and in those animals that received the NP vaccine in addition to disc puncture. These findings therefore indicate that it is possible to elicit immune responses against NP antigens in adult animals, and that these immune responses may contribute to accelerated development of IDD in a novel immune-induced and accelerated IDD model. 

Traditional design galleries enable users to search for examples based on surface attributes (e.g., color or style), and largely obscure underlying principles (e.g., hierarchy or readability). We conducted three studies to explore how galleries could be constructed to help novices learn key design principles. Study 1 revealed that novices gain perspective by observing how designs evolve throughout a process. Study 2 found that novices are better at identifying design issues when viewing iterations that show improvements for just one principle at a time, rather than multiple. Building on these insights, we created ProcessGallery, a tool that enables users to browse contrasting pairs of early-and-late iterations of designs that highlight key improvements organized by design principles. In Study 3, a within-subjects experiment, sixteen participants iterated on a seed design after viewing examples in ProcessGallery versus a traditional gallery. Using ProcessGallery, participants found more appropriate examples, assessed designs better, and preferred ProcessGallery for learning compared to a traditional gallery.