Felice Dell’ORletta

Although AI systems are becoming increasingly common in the workplace, research on their integration into human teams remains limited. In particular, little is known about how the embodiment of artificial agents shapes collaboration and performance in non-routine analytical tasks. To address this gap, we examine how different degrees of embodiment affect team performance and conversational dynamics in a real-life escape room. Teams composed of either three humans or two humans and an artificial agent (a Box, an Avatar, or a hyper-realistic humanoid) worked together to escape the room within a time limit. Our findings show that artificial agents have an uneven impact on team outcomes, with some mixed human–AI teams performing exceptionally well and others markedly worse. Human-only teams, by contrast, display more consistent performance: they are more likely to complete all tasks successfully, although they take longer and commit more errors. We also document a suggestive non-linear relationship between embodiment and team performance. Teams interacting with more embodied agents display conversational patterns that more closely resemble human–human dialogue. Together, these findings show that embodied AI shapes collaboration in complex ways, reinforcing evidence that social cues critically guide teamwork dynamics.

The paper introduces Parallel Trees, a novel multilingual treebank collection that includes 20 treebanks for 10 languages. The distinguishing property of this resource is that the sentences of each language are annotated using two syntactic representation paradigms (SRPs), respectively based on the notions of dependency and constituency. By aligning the annotations of existing resources, Parallel Trees represents an example of exploiting pre-existing treebanks to adapt them to novel applications. To illustrate its potential, we present a case study where the resource is employed as a benchmark to investigate whether and how BERT, one of the first prominent neural language models (NLMs), is sensitive to the dependency- and constituency-based approaches for representing the syntactic structure of a sentence. The case study results indicate that the model’s sensitivity fluctuates across languages and experimental settings. The unique nature of the Parallel Trees resource creates the prerequisites for innovative studies comparing dependency and phrase-structure trees, allowing for more focused investigations without the interference of lexical variation.

Mental reconstruction (MRC) and Free Recall (FR) have been recognized for enhancing the quality of witness statements. However, the mechanisms underlying this association remain insufficiently understood. This study explores how the time allocated to MRC and FR and variations in educational level influence the quality of eyewitness testimonies. Testimony quality is evaluated based on manually annotated content information provided by experts in testimony assessment, which measures adherence to the events. This is further complemented by fine-grained linguistic features, automatically extracted using linguistic analysis tools, to capture stylistic aspects. As a proof of concept, the analysis is performed on a corpus of 96 testimonies in Spanish describing two robbery cases. The results suggest that both mental reconstruction and narration times positively impact the accuracy of testimonies, as inaccuracies predominantly involve peripheral details. Furthermore, while the study confirms that educational level affects testimony quality, no significant differences were observed in the frequency of erroneous reports. This study contributes to the understanding of the relationship between cognitive strategies and the accuracy of witness statements, proposing an analysis approach applicable to forensic psychology for witness assessment.