Metraipolis › archive › dc_db317709b5f7
Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices — arXiv:2609.35070
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35070
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:15.923Z
- SHA-256 of the archived text
19cc81902a67a0141cb852802a07f4874e8a5396995424368ddbefe5bf0cd98b- Stable URL of this page
https://metraipolis.com/documento/dc_db317709b5f7
How to cite
Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices — arXiv:2609.35070 — arXiv (en), https://arxiv.org/abs/2609.35070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db317709b5f7 (Metraipolis archive dc_db317709b5f7, sha256 19cc81902a67a0141cb852802a07f4874e8a5396995424368ddbefe5bf0cd98b)
BibTeX
@misc{dcdb317709b5f7,
title = {Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices — arXiv:2609.35070},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35070},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db317709b5f7; sha256 19cc81902a67a0141cb852802a07f4874e8a5396995424368ddbefe5bf0cd98b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Evaluations of Large Language Models (LLMs) morality typically consider decisions in isolation, thus overlooking whether an individual's unrelated prior conduct influences the model's subsequent choices. This leaves open the question of whether, and to what extent, moral history shapes LLM decisional behaviors. Prior work on human moral decision-making shows that past behavior can influence subsequent moral choices. Building on this observation, we investigate whether analogous effects emerge in LLMs in two complementary ways: at the behavioral level, through the model's observable responses, and at the representation level, through its latent internal representations. We introduce MoralLedger, a framework for studying how an actor's moral history shapes actions for LLMs' behaviors under a fixed decision context. At the behavioral level, we find that prior moral histories systematically alter subsequent choices as a function of their valence and intensity. At the internal representation level, these histories induce a linearly recoverable direction in the residual stream that generalizes to held-out examples. Intervening along this direction on neutral-history prompts produces two-sided intensity-dependent changes in subsequent choices, with effects that are stronger than those induced by prompting alone or by favorable-nonmoral direction. To our knowledge, this is the first demonstration that a latent representation of an actor's prior moral conduct can provide signed inference-time control over a moral decision. Our MoralLedger extends moral evaluation beyond static dilemmas, establishing moral history as both a source of behavioral sensitivity and a causal target for auditing and controlling moral behavior in LLMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.35070 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:03.255Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).