Metraipolis › archive › dc_b3ea82decbe4

Functional-Group Knowledge Is Structured in Language Models Before It Is Spoken — arXiv:2611.03684

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03684
License (as archived)
CC0-1.0
Archived
2026-11-04T18:33:38.156Z
SHA-256 of the archived text
a3f797d7db15ee2b3fd9f434118391a5f039ba92b588446f0e87bd5f45beca83
Stable URL of this page
https://metraipolis.com/documento/dc_b3ea82decbe4

How to cite

Functional-Group Knowledge Is Structured in Language Models Before It Is Spoken — arXiv:2611.03684 — arXiv (en), https://arxiv.org/abs/2611.03684 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3ea82decbe4 (Metraipolis archive dc_b3ea82decbe4, sha256 a3f797d7db15ee2b3fd9f434118391a5f039ba92b588446f0e87bd5f45beca83)
BibTeX
@misc{dcb3ea82decbe4,
  title = {Functional-Group Knowledge Is Structured in Language Models Before It Is Spoken — arXiv:2611.03684},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03684},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3ea82decbe4; sha256 a3f797d7db15ee2b3fd9f434118391a5f039ba92b588446f0e87bd5f45beca83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03684. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models serve as the reasoning core of agents for chemistry and materials science, where they must interpret molecular structure before planning syntheses or proposing materials. Yet their outputs show only what they say, not what they know. Given a prompt such as ``The primary functional group in 1-Fluorobutane (CCCCF) is'', a small general-purpose model may answer ``the alkyne group'' instead of an alkyl fluoride. The output alone cannot tell whether the model failed to recognize the fluorine or recognized it and failed to say so. We address this by reading the internal representations of five open-source models on prompts covering 92 molecules and 20 functional groups. Even without chemistry training, the models organize functional groups by chemical family, and they encode chemical differences as consistent directions. The shift from thioether ($\mathrm{R{-}S{-}R'}$) to thiol ($\mathrm{R{-}SH}$), added to ether ($\mathrm{R{-}O{-}R'}$), lands nearest alcohol ($\mathrm{R{-}OH}$). This structure emerges abruptly in the middle layers, where representations shift from tracking the wording of the prompt to tracking the functional group. The base model names the correct functional group in only 58.5\% of prompts, the lowest of the five, yet it encodes functional-group families and preserves chemically meaningful patterns. Its errors are mostly failures to answer rather than wrong answers. Functional-group knowledge is structured in the model before it is spoken. Chemistry fine-tuning reorganizes it, making functional groups rather than prompt wording dominate the representation. These results suggest that evaluating chemical language models through outputs alone can underestimate the chemical information they encode. Representation analysis can distinguish a lack of knowledge from a failure to express it, which matters when choosing or adapting models for chemical agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.03684 — 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 2026-11-04T18:32:37.229Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).