Backend
Learning to Decide with AI Assistance under Human-Alignment
arXiv cs.HC0 views
arXiv:2605.12646v3 Announce Type: replace-cross Abstract: It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that decision-makers often struggle to determine when to trust a prediction based solely on this communicated confidence. In this context, recent theoretical and empirical work suggests a positive correlation between the utility of AI-assisted decision-making and the degree of alignment between the AI confidence and the decision-makers' confidence in their own predictions. Crucially, these findings do not yet elucidate the extent to which this alignment influences the complexity of learning to make optimal decisions through repeated interactions. In this paper, we address this question in the canonical case of binary predictions and binary decisions. We first show that this problem is equivalent to a two-armed online contextual learning problem with full feedback, and establish a lower bound of $\Omega (\sqrt{|H| \cdot |B| \cdot T} )$ on the expected regret any learner can attain, where $H$ and $B$ denote the sets of human and AI confidence values. We then demonstrate that, under perfect alignment between AI and human confidence, a learner can attain an expected regret of $O(\sqrt{|H| \cdot T\log T})$ and, when $\sqrt{|H|} = O(\log T)$ and $B$ is countable, a non-trivial generalization of the Dvoretzky-Kiefer-Wolfowitz inequality improves the regret bound to $O(\sqrt{T\log T})$. Taken together, these results reveal that alignment can reduce the complexity of learning to make decisions with AI assistance. Experiments on real data from two different human-subject studies where participants solve simple decision-making tasks assisted by AI models show that our theoretical results are robust to violations of perfect alignment.
Source:https://arxiv.org/abs/2605.12646PreviousHow Far Does Online RL Generalize in Mobile GUI Agents? A Controlled Study with AndroidWorld-GeneralizationNextCaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
Related posts
Drawing 28 questions from an 84-question bank: how I score a deadly sins quiz
0dev.to
Count tokens before you call the LLM: tiktoken encodings, token budgets and chunking, with real numbers
0dev.to
![Quadruped Robot Software — Ch.10: Quadruped AI and Physical AI [KR]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ffiibwtdu8wij6gnnuoyc.png)
Quadruped Robot Software — Ch.10: Quadruped AI and Physical AI [KR]
0dev.to
Signal #138: Java4Shell Hits AVX-512 JDKs; GPT-6.2 Astra and Sol Ship
0dev.to

Check Support Emails Before the LLM: Wolf Defender in Apache Camel
0dev.to

The Librarian, the Missing Book, and the AI with a Master Key. Sentinel IR MCP
0dev.to