# Belief Filtering for Epistemic Control in Linguistic State Space

arXiv: https://arxiv.org/abs/2505.04927 · HTML: https://mlsanity.com/paper/2505.04927/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 3 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 2 of 2)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Theoretical Foundations for Semantic Cognition in Artificial Intelligence](https://mlsanity.com/paper/2504.21218/) (2025)

## Built on by (most cited first, 2 of 2)

- [Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activation](https://mlsanity.com/paper/2510.10042/) (2025)
- [Belief Injection for Epistemic Control in Linguistic State Space](https://mlsanity.com/paper/2505.07693/) (2025)

## Abstract (arXiv)

We examine belief filtering as a mechanism for the epistemic control of artificial agents, focusing on the regulation of internal cognitive states represented as linguistic expressions. This mechanism is developed within the Semantic Manifold framework, where belief states are dynamic, structured ensembles of natural language fragments. Belief filters act as content-aware operations on these fragments across various cognitive transitions. This paper illustrates how the inherent interpretability and modularity of such a linguistically-grounded cognitive architecture directly enable belief filtering, offering a principled approach to agent regulation. The study highlights the potential for enhancing AI safety and alignment through structured interventions in an agent's internal semantic space and points to new directions for architecturally embedded cognitive governance.