This study provides ERP and oscillatory dynamics data associated with the comprehension of narratives involving counterfactual events. Participants were given short stories describing an initial situation ("Marta wanted to plant flowers in her garden...."), followed by a critical sentence describing a new situation in either a factual ("Since she found a spade, she started to dig a hole") or counterfactual format ("If she had found a spade, she would have started to dig a hole"), and then a continuation sentence that was either related to the initial situation ("she bought a spade") or to the new one ("she planted roses"). The ERPs recorded for the continuation sentences related to the initial situation showed larger negativity after factuals than after counterfactuals, suggesting that the counterfactual's presupposition - the events did not occur - prevents updating the here-and-now of discourse. By contrast, continuation sentences related to the new situation elicited similar ERPs under both factual and counterfactual contexts, suggesting that counterfactuals also activate momentarily an alternative "as if" meaning. However, the reduction of gamma power following counterfactuals, suggests that the "as if" meaning is not integrated into the discourse, nor does it contribute to semantic unification processes.
LINK
This article investigates gender bias in narratives generated by Large Language Models (LLMs) through a two-phase study. Building on our existing work in narrative generation, we employ a structured methodology to analyze the influence of protagonist gender on both the generation and classification of fictional stories. In Phase 1, factual narratives were generated using six LLMs, guided by predefined narrative structures (Hero's Journey and Heroine's Journey). Gender bias was quantified through specialized metrics and statistical analyses, revealing significant disparities in protagonist gender distribution and associations with narrative archetypes. In Phase 2, counterfactual narratives were constructed by altering the protagonists’ genders while preserving all other narrative elements. These narratives were then classified by the same LLMs to assess how gender influences their interpretation of narrative structures. Results indicate that LLMs exhibit difficulty in disentangling the protagonist's gender from the narrative structure, often using gender as a heuristic to classify stories. Male protagonists in emotionally driven narratives were frequently misclassified as following the Heroine's Journey, while female protagonists in logic-driven conflicts were misclassified as adhering to the Hero's Journey. These findings provide empirical evidence of embedded gender biases in LLM-generated narratives, highlighting the need for bias mitigation strategies in AI-driven storytelling to promote diversity and inclusivity in computational narrative generation.
MULTIFILE
In this paper, we explore the design of web-based advice robots to enhance users' confidence in acting upon the provided advice. Drawing from research on algorithm acceptance and explainable AI, we hypothesise four design principles that may encourage interactivity and exploration, thus fostering users' confidence to act. Through a value-oriented prototype experiment and valueoriented semi-structured interviews, we tested these principles, confirming three of them and identifying an additional principle. The four resulting principles: (1) put context questions and resulting advice on one page and allow live, iterative exploration, (2) use action or change oriented questions to adjust the input parameters, (3) actively offer alternative scenarios based on counterfactuals, and (4) show all options instead of only the recommended one(s), appear to contribute to the values of agency and trust. Our study integrates the Design Science Research approach with a Value Sensitive Design approach.
DOCUMENT
