arXiv subjects

Julian Berger

Publications and source records attributed to Julian Berger.

6 recordsLinked to original sources

arXiv2026

Beyond AI advice -- independent aggregation boosts human-AI accuracy

Artificial intelligence (AI) is broadly deployed as an advisor to human decision-makers: AI recommends a decision and a human accepts or rejects the advice. This approach, however, has several limitations: People frequently ignore accurate advice and rely too much on inaccurate advice, and their decision-making skills may deteriorate over time. Here, we compare the AI-as-advisor approach to the hybrid confirmation tree (HCT), an alternative strategy that preserves the independence of human and AI judgments. The HCT elicits a human judgment and an AI judgment independently of each other. If they agree, that decision is accepted. If not, a second human breaks the tie. For the comparison, we used 10 datasets from various domains, including medical diagnostics and misinformation discernment, and a subset of four datasets in which AI also explained its decision. The HCT outperformed the AI-as-advisor approach in all datasets. The HCT also performed better in almost all cases in which AI offered an explanation of its judgment. Using signal detection theory to interpret these results, we find that the HCT outperforms the AI-as-advisor approach because people cannot discriminate well enough between correct and incorrect AI advice. Overall, the HCT is a robust, accurate, and transparent alternative to the AI-as-advisor approach, offering a simple mechanism to tap into the wisdom of hybrid crowds.

cs.HC↗

arXiv2026

The hybrid confirmation tree: A robust strategy for hybrid intelligence

Combining human and artificial intelligence (AI) is a potentially powerful approach to boost decision accuracy. However, few such approaches exist that effectively integrate both types of intelligence while maintaining human agency. Here, we introduce and evaluate the hybrid confirmation tree, a simple aggregation strategy that compares the independent decisions of both a human and AI, with disagreements triggering a second human tiebreaker. Through analytical derivations, we show that the hybrid confirmation tree can match and exceed the accuracy of a three-person human majority vote while requiring fewer human inputs, particularly when AI accuracy is comparable to or exceeds human accuracy. We analytically demonstrate that the hybrid confirmation tree's ability to achieve complementarity -- outperforming individual humans, AI, and the majority vote -- is maximized when human and AI accuracies are similar and their decisions are not overly correlated. Empirical reanalysis of six real-world datasets (covering skin cancer diagnosis, deepfake detection, geopolitical forecasting, and criminal rearrest) validates these findings, showing that the hybrid confirmation tree improves accuracy over the majority vote by up to 10 percentage points while reducing the cost of decision making by 28--44$\%$. Furthermore, the hybrid confirmation tree provides greater flexibility in navigating true and false positive trade-offs compared to fixed human-only heuristics like hierarchies and polyarchies. The hybrid confirmation tree emerges as a practical, efficient, and robust strategy for hybrid collective intelligence that maintains human agency.

cs.HC↗

arXiv2025

Human learning is an understudied but promising lever for boosting human--AI synergy

Humans collaborating with artificial intelligence (AI) hold the promise of achieving superior outcomes compared to either acting alone (i.e., human--AI synergy). However, the conditions that facilitate such synergy when humans are advised by AI are not well understood. A recent meta-analysis showed that, on average, human--AI combinations do not outperform the better individual agent. We argue that this pessimistic conclusion arises from insufficient attention to human learning in experimental designs. To substantiate this claim, we re-analyzed all 74 studies included in the original meta-analysis and found that most previous research overlooked design features that foster human learning (e.g., outcome feedback to participants). Our re-analysis further revealed that studies providing outcome feedback show tentatively higher synergy than those without outcome feedback. Crucially, feedback paired with AI explanations was associated with positive synergy, while explanations without feedback were associated with negative synergy---suggesting that explanations improve synergy mainly when humans can learn to verify the AI's reliability through feedback. Our re-analysis suggests that the current literature underestimates the potential of human--AI collaboration because it predominantly relies on paradigms that do not facilitate human learning, thus hindering humans from effectively adapting their collaboration strategies. However, experiments directly varying learning opportunities are needed for stronger, causal conclusions. We advocate for a paradigm shift in human--AI interaction research that explicitly addresses human learning and thus enhances our understanding of and support for successful human--AI collaboration.

cs.HC↗

arXiv2025

Strategic Network Creation for Enabling Greedy Routing

Today we rely on networks that are created and maintained by smart devices. For such networks, there is no governing central authority but instead the network structure is shaped by the decisions of selfish intelligent agents. A key property of such communication networks is that they should be easy to navigate for routing data. For this, a common approach is greedy routing, where every device simply routes data to a neighbor that is closer to the respective destination. Networks of intelligent agents can be analyzed via a game-theoretic approach and in the last decades many variants of network creation games have been proposed and analyzed. In this paper we present the first game-theoretic network creation model that incorporates greedy routing, i.e., the strategic agents in our model are embedded in some metric space and strive for creating a network among themselves where all-pairs greedy routing is enabled. Besides this, the agents optimize their connection quality within the created network by aiming for greedy routing paths with low stretch. For our model, we analyze the existence of (approximate)-equilibria and the computational hardness in different underlying metric spaces. E.g., we characterize the set of equilibria in 1-2-metrics and tree metrics and show that Nash equilibria always exist. For Euclidean space, the setting which is most relevant in practice, we prove that equilibria are not guaranteed to exist but that the well-known $Θ$-graph construction yields networks having a low stretch that are game-theoretically almost stable. For general metric spaces, we show that approximate equilibria exist where the approximation factor depends on the cost of maintaining any link.

cs.GT↗

arXiv2020

Maps for Learning Indexable Classes

We study learning of indexed families from positive data where a learner can freely choose a hypothesis space (with uniformly decidable membership) comprising at least the languages to be learned. This abstracts a very universal learning task which can be found in many areas, for example learning of (subsets of) regular languages or learning of natural languages. We are interested in various restrictions on learning, such as consistency, conservativeness or set-drivenness, exemplifying various natural learning restrictions. Building on previous results from the literature, we provide several maps (depictions of all pairwise relations) of various groups of learning criteria, including a map for monotonicity restrictions and similar criteria and a map for restrictions on data presentation. Furthermore, we consider, for various learning criteria, whether learners can be assumed consistent.

cs.LG↗

arXiv2020

Learning Languages with Decidable Hypotheses

In language learning in the limit, the most common type of hypothesis is to give an enumerator for a language. This so-called $W$-index allows for naming arbitrary computably enumerable languages, with the drawback that even the membership problem is undecidable. In this paper we use a different system which allows for naming arbitrary decidable languages, namely programs for characteristic functions (called $C$-indices). These indices have the drawback that it is now not decidable whether a given hypothesis is even a legal $C$-index. In this first analysis of learning with $C$-indices, we give a structured account of the learning power of various restrictions employing $C$-indices, also when compared with $W$-indices. We establish a hierarchy of learning power depending on whether $C$-indices are required (a) on all outputs; (b) only on outputs relevant for the class to be learned and (c) only in the limit as final, correct hypotheses. Furthermore, all these settings are weaker than learning with $W$-indices (even when restricted to classes of computable languages). We analyze all these questions also in relation to the mode of data presentation. Finally, we also ask about the relation of semantic versus syntactic convergence and derive the map of pairwise relations for these two kinds of convergence coupled with various forms of data presentation.

cs.LO↗