Understanding the Mechanism of Altruism in Large Language Models

Shuhuai Zhang, Shu Wang, Zijun Yao, Chuanhao Li, Xiaozhi Wang, Songfa Zhong and Tracy Xiao Liu

Papers from arXiv.org

Abstract: Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such behavior remain poorly understood. We investigate the mechanisms underlying LLM altruism using sparse autoencoders (SAEs). In a standard Dictator Game, minimal-pair prompts that differ only in social stance (generous versus selfish) induce large, economically meaningful shifts in allocations. Leveraging this contrast, we identify a set of SAE features (0.024% of all features across the model's layers) whose activations are strongly associated with the behavioral shift. To interpret these features, we use benchmark tasks motivated by dual-process theories to classify a subset as primarily heuristic (System 1) or primarily deliberative (System 2). Causal interventions validate their functional role: activation patching and continuous steering of this feature direction reliably shift allocation distributions, with System 2 features exerting a more proximal influence on the model's final output than System 1 features. The same steering direction generalizes across multiple social-preference games. Together, these results enhance our understanding of artificial cognition by translating altruistic behaviors into identifiable network states and provide a framework for aligning LLM behavior with human values, thereby informing more transparent and value-aligned deployment.

Date: 2026-04
New Economics Papers: this item is included in nep-ain, nep-evo, nep-exp and nep-neu
References: Add references at CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2604.19260 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2604.19260

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().