Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility aggregation, yielding unstable implicit weights. We show empirically and theoretically that this aggregation-specific \emph{weighting noise} can create large score shifts when stakeholder satisfaction is dispersed; in our experiments, these weight-induced shifts also increase with stakeholder count. We propose \textsc{DecompR}: counterfactual-calibrated weights are fixed from query structure before candidate scoring, while per-role utilities are estimated independently, removing candidate-dependent weight drift and reducing estimation noise.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A knapsack for collective decision-making
Collective decision-making is the process through which diverse stakeholders reach a joint decision. Within societal settings, one example is participatory budgeting, where constituents decide on the funding of public pr…
Decision MakingDecision Making Under UncertaintyBehavioural feasible set: Value alignment constraints on AI decision support
When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support de…
Aligning Large Language Models with Healthcare Stakeholders: A Pathway to Trustworthy AI Integration
The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare w…
Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies
Cities are not monolithic; they are arenas of negotiation among groups that hold varying needs, values, and experiences. Conventional methods of urban assessment -- from standardized surveys to AI-driven evaluations -- f…
FairnessPluralistic Alignment Over Time
If an AI system makes decisions over time, how should we evaluate how aligned it is with a group of stakeholders (who may have conflicting values and preferences)? In this position paper, we advocate for consideration of…
FairnessPosition