Identifying Context-Specific Values via Hybrid Intelligence

Liscio, Enrico; Jonker, Catholijn M.; Murukannaiah, Pradeep K.

doi:10.3233/faia220223

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, value identification is the process of identifying the set of values relevant to a decision context. Inspired by Value Sensitive Design [11], we advocate for methods that take into account the decision context [22,24] and involve stakeholders, e.g., via data-driven methods [8,40,41]. Subsequently, value estimation is the process of determining an individual's value preferences over the identified values.…”

Section: Hybrid Value Inferencementioning

confidence: 99%

Inferring Values via Hybrid Intelligence

Liscio,

Lera-Leri,

Bistaffa

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Values, such as freedom and safety, are the core motivations that guide us humans. A prerequisite for creating value-aligned multiagent systems that involve humans and artificial agents is value inference, the process of identifying values and reasoning about human value preferences. We introduce a framework that connects the value inference steps, and motivate why a hybrid intelligence approach is instrumental for its success. We also highlight the multidisciplinary research challenges that hybrid value inference entails.

show abstract

Section: Hybrid Value Inferencementioning

confidence: 99%

Inferring Values via Hybrid Intelligence

Liscio,

Lera-Leri,

Bistaffa

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…However, both the annotation and extraction of values remain difficult, with specific questions relating to the granularity of the value labels (Kiesel et al, 2022), their transfer to new domains , and how classifiers understand morality in language (Liscio et al, 2023). Moreover, large variances exist between the frequency of values across domain (Kennedy et al, 2021), and even the relevance of values differs depending on the domain (Bouman et al, 2018;Liscio et al, 2021). However, users can still be represented inside each domain by examining relative frequencies inside value profiles, as stipulated by .…”

Section: Value Estimationmentioning

confidence: 99%

Do Differences in Values Influence Disagreements in Online Discussions?

van der Meer,

Vossen,

Jonker

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Disagreements are common in online discussions. Disagreement may foster collaboration and improve the quality of a discussion under some conditions. Although there exist methods for recognizing disagreement, a deeper understanding of factors that influence disagreement is lacking in the literature. We investigate a hypothesis that differences in personal values are indicative of disagreement in online discussions. We show how state-of-the-art models can be used for estimating values in online discussions and how the estimated values can be aggregated into value profiles. We evaluate the estimated value profiles based on human-annotated agreement labels. We find that the dissimilarity of value profiles correlates with disagreement in specific cases. We also find that including value information in agreement prediction improves performance.

show abstract

“…When values are imbued in systems, aggregating values into a single outcome may improve ethical decision making in STS [22]. However, reasoning about values is challenging [17], and stakeholders could have personal preferences between different values [16,21]. Value preferences of some stakeholders may conflict with value preferences of other stakeholders, or values may conflict with norms [10,25].…”

Section: Ongoing Work: Operationalising Ethical Principlesmentioning

confidence: 99%

“…Our current work assumes each stakeholder's order of value preferences is fixed. However, preferences may change [8,17]. Future work could involve expanding our current simulations to incorporate contextual values and changing value preferences.…”

Section: Next Steps: Incorporating Contextmentioning

confidence: 99%