# Reliable Fusion of Conflicting Experts

arXiv: https://arxiv.org/abs/2609.27913 · HTML: https://mlsanity.com/paper/2609.27913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures](https://mlsanity.com/paper/1905.08550/) (2019)
- [Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models](https://mlsanity.com/paper/2411.00492/) (2024)
- [Building Expressive and Tractable Probabilistic Generative Models: A Review](https://mlsanity.com/paper/2402.00759/) (2024)
- [Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits](https://mlsanity.com/paper/2403.03281/) (2024)
- [Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making](https://mlsanity.com/paper/2305.01063/) (2023)
- [Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits](https://mlsanity.com/paper/2603.26629/) (2026)

## Abstract (arXiv)

We study the problem of aggregating opinions from multiple black-box experts in noisy, conflict-prone settings where expert reliability varies across inputs. Static aggregation methods, such as majority voting, fail to capture this variability and often yield unreliable outcomes under disagreement. We propose a tractable, probabilistic-circuit-based fusion framework that dynamically combines expert responses using context-specific credibility estimates, enabling principled and reliable reasoning. The framework is agnostic to the underlying experts and does not require access to their internal representations or any retraining. We empirically validate our approach on multiple-choice question answering tasks using multiple LLMs as experts, comparing against individual models and static ensemble baselines. Our method consistently improves predictive performance and produces more reliable decisions under conflict, highlighting the effectiveness of context-aware credibility modeling for robust multi-expert fusion.