Metraipolis › archive › dc_bf365c30c5be
Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology — arXiv:2610.12022
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12022
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:03:28.732Z
- SHA-256 of the archived text
4aa478f89853da75fb943bc562328ef75dfbbdc3a1f0f1852621b6fc76ed0c38- Stable URL of this page
https://metraipolis.com/documento/dc_bf365c30c5be
How to cite
Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology — arXiv:2610.12022 — arXiv (en), https://arxiv.org/abs/2610.12022 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf365c30c5be (Metraipolis archive dc_bf365c30c5be, sha256 4aa478f89853da75fb943bc562328ef75dfbbdc3a1f0f1852621b6fc76ed0c38)
BibTeX
@misc{dcbf365c30c5be,
title = {Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology — arXiv:2610.12022},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12022},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf365c30c5be; sha256 4aa478f89853da75fb943bc562328ef75dfbbdc3a1f0f1852621b6fc76ed0c38},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12022. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external events to the causes and reasons of agents' social behaviors, plays a critical role. These processes involve judgments of social cause, responsibility, and blame/credit to agents. Although attributional models are well-studied in social psychology and cognition through Attribution Theory, social attribution remains underexplored in AI, particularly LLM social reasoning. This paper provides the first systematic exploration of LLM social attribution. Our work focuses on responsibility and blame attributions, examining current LLMs' judgments and their underlying internal mechanisms. Guided by attribution theory, we construct a social attribution benchmark consisting of a Vignette subset based on classic scenarios from attribution theory research and a Reality subset based on real-world social narratives, yielding 7,639 responsibility/blame judgment questions. On this basis, we evaluate 32 representative LLMs and 5 basic non-LLM baselines. To further explore the internal mechanisms underlying the LLM judgment process, we develop a probing-based methodology to investigate the latent-space representations of 5 key attribution dimensions and the consistency of their influences on LLM judgments compared to those in human social attribution. Our research findings reveal that current LLMs exhibit measurable but incomplete agreement with human responsibility and blame judgments, and meanwhile, this agreement is positively correlated with model size. Some attribution dimensions are systematically decodable from specific positions in LLM hidden states, and their influences on the final judgment are consistent with those indicated by human Attribution Theory. The dataset and associated code are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.12022 — 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 2026-10-09T05:47:02.000Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).