# Shaping Scientific Explanations to Expert Perspectives with Persona-Conditioned Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.21846 · HTML: https://mlsanity.com/paper/2603.21846/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 14 of 14)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations](https://mlsanity.com/paper/2207.04154/) (2022)
- [Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs](https://mlsanity.com/paper/2101.09824/) (2021)
- [OWL2Vec*: Embedding of OWL Ontologies](https://mlsanity.com/paper/2009.14654/) (2020)
- [Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs](https://mlsanity.com/paper/2103.10367/) (2021)
- [Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research](https://mlsanity.com/paper/2211.15343/) (2022)
- [The Impostor is Among Us: Can Large Language Models Capture the Complexity of Human Personas?](https://mlsanity.com/paper/2501.04543/) (2025)
- [Rewarding Explainability in Drug Repurposing with Knowledge Graphs](https://mlsanity.com/paper/2509.02276/) (2025)

## Abstract (arXiv)

Explainable AI is increasingly important to scientific discovery. However, existing methods largely ignore that explanation quality is not universal: experts differ in how they assess evidence, prioritize mechanisms, and construct explanatory narratives. We introduce perspective-conditioned explanations, a framework for adapting explanation generation to epistemic variation in expert judgment. Using knowledge graph reasoning paths in drug discovery, we show that preferences organize into coherent epistemic perspectives that can be captured by agentic personas, representations of how experts evaluate explanations. Persona-aligned rewards then guide reinforcement learning-based explanation generation without large-scale expert supervision. Expert user studies show that perspective-conditioned explanations are preferred over general-purpose explanations and improve perceived relevance and validity. Moreover, they match or exceed state-of-the-art predictive performance and reduce expert feedback time by two orders of magnitude. Together, these findings demonstrate that explanation quality is perspective-dependent and that modeling this variation enables scalable and human-aligned explanation generation for scientific discovery.