Metraipolis › archive › dc_8ffd8f47d422
The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment — arXiv:2609.16993
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16993
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:38:46.324Z
- SHA-256 of the archived text
3683eeda440d452b1d2dd09a545b3c83f9bfd0187547238deb8ef822264a7d59- Stable URL of this page
https://metraipolis.com/documento/dc_8ffd8f47d422
How to cite
The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment — arXiv:2609.16993 — arXiv (en), https://arxiv.org/abs/2609.16993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ffd8f47d422 (Metraipolis archive dc_8ffd8f47d422, sha256 3683eeda440d452b1d2dd09a545b3c83f9bfd0187547238deb8ef822264a7d59)
BibTeX
@misc{dc8ffd8f47d422,
title = {The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment — arXiv:2609.16993},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16993},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ffd8f47d422; sha256 3683eeda440d452b1d2dd09a545b3c83f9bfd0187547238deb8ef822264a7d59},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models are now common in student assessment, but we know little about how student demographics affect their use. Sometimes, considering student demographics may be necessary -- for example, to improve readability for users with lower educational levels. However, it also risks being a cause of discrimination, e.g., when assigning lower scores to students from lower socioeconomic backgrounds. We set up controlled prompts to test 1) explicit demographic effects, where we mention demographic details directly, and 2) implicit effects, where we use conversation history as a demographic signal. We test these settings in three tasks: Automated Essay Scoring, Formative Feedback, and Metalinguistic Question Answering. We test six state-of-the-art LLMs on these tasks. In both explicit and implicit cases, the models pick up on demographic cues and can change their scoring, feedback, and answers accordingly. We find that LLMs frequently adjust the readability of feedback to education levels when these are explicitly mentioned. On the other hand, implicit conditions produce unpredictable biases, such as in question answering, where responses from lower-education levels receive lower sentiment scores. Our results provide clear evidence of demographic sensitivity in LLMs for educational assessment tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 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/2609.16993 — 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 2026-10-15T18:03:09.715Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).