Metraipolis › archive › dc_3fc18bf2bff8
Computation, not weight access: large language models as auditors of clinical prediction networks — arXiv:2611.07847
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07847
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:42.021Z
- SHA-256 of the archived text
4a08a62f54a4a8cec489fed4937fddbce06c0474e307576a974d81f6dc50d962- Stable URL of this page
https://metraipolis.com/documento/dc_3fc18bf2bff8
How to cite
Computation, not weight access: large language models as auditors of clinical prediction networks — arXiv:2611.07847 — arXiv (en), https://arxiv.org/abs/2611.07847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fc18bf2bff8 (Metraipolis archive dc_3fc18bf2bff8, sha256 4a08a62f54a4a8cec489fed4937fddbce06c0474e307576a974d81f6dc50d962)
BibTeX
@misc{dc3fc18bf2bff8,
title = {Computation, not weight access: large language models as auditors of clinical prediction networks — arXiv:2611.07847},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07847},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fc18bf2bff8; sha256 4a08a62f54a4a8cec489fed4937fddbce06c0474e307576a974d81f6dc50d962},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone. Public demonstrations, however, mixed reading raw weights with running code. We separated these conditions in internally pre-specified simulation experiments. Tanh networks of 105 to 38,401 weights were trained on simulated cohorts of patients with subarachnoid haemorrhage, each with a planted relationship or none, and one network was trained on labels that under-recorded deaths in a subgroup. GPT-6 Astra and four other GPT models answered single prompts under a default or an explicit system instruction, either with the weights in the prompt and no tools, or with a calculation-only tool that exposed the weights (white box) or only the network's predictions (black box). Without tools, Astra recovered planted relationships in 353-weight networks but became unreliable at 3,457 weights, and under the default instruction it declined 11 of 12 audit and repair tasks as unidentifiable; the explicit instruction removed these refusals. With the tool, it recovered the planted relationship in all 29 runs on networks of up to 38,401 weights, raised no false alarm in 15 runs on null networks, and found the biased subgroup in 6 of 6 runs. Black-box access performed as well as white-box access, and other GPT-6 models read as accurately. A well-designed script matched the comparator models on the audit and the best LLM repair. For auditing these networks, what mattered was computation and elicitation, not access to the weights. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.07847 — 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 2026-11-06T14:18:42.691Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).