Metraipolis › archive › dc_4e3f100e240f

Mimicry without understanding: the origins of decision bias in large language models — arXiv:2608.12339

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12339
License (as archived): CC0-1.0
Archived: 2026-10-19T04:17:50.958Z
SHA-256 of the archived text: dbc297fe4c366fa0a138356a1aeeb2add329ff350e0d444c6f83181ca1dc690f
Stable URL of this page: https://metraipolis.com/documento/dc_4e3f100e240f

How to cite

Mimicry without understanding: the origins of decision bias in large language models — arXiv:2608.12339 — arXiv (en), https://arxiv.org/abs/2608.12339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e3f100e240f (Metraipolis archive dc_4e3f100e240f, sha256 dbc297fe4c366fa0a138356a1aeeb2add329ff350e0d444c6f83181ca1dc690f)

BibTeX

@misc{dc4e3f100e240f,
  title = {Mimicry without understanding: the origins of decision bias in large language models — arXiv:2608.12339},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12339},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e3f100e240f; sha256 dbc297fe4c366fa0a138356a1aeeb2add329ff350e0d444c6f83181ca1dc690f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases. We examined two mechanisms through which such biases can be generated even when human preferences (in the training data) are not biased or when they are correctly categorized as being biased. The first is faulty mimicry of preferences based on human behavior: this involves LLMs inferring human preferences even when behaviors are logically unrelated to preferences. The second is mimicry of explicitly biased human behaviors. In four studies focusing on economic biases, we find that ChatGPT-4o and Qwen exhibited social proof biases even when prompted with reports of human behaviors that were clearly non-indicative of individuals' actual preferences. LLMs also displayed loss aversion when it was explicitly described as a bias. Indeed, when prompted with detailed scientific reports, the extent of the bias (i.e., loss aversion) in the scientific report predicted LLMs' own subsequent bias. Scientific papers of biases can thus become self-fulfilling prophecies, at least when it comes to LLMs' responses. The current study goes beyond fleshing out LLM biases and sheds light on the underlying component processes.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.12339 — 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 2026-10-19T04:13:06.644Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).