Metraipolis › archive › dc_f674a64eaf97

CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition — arXiv:2610.27901

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27901
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:08.173Z
SHA-256 of the archived text
cedc220ae1255b1afccd3477afebde13ae65df8305a31746932c3bf79412a192
Stable URL of this page
https://metraipolis.com/documento/dc_f674a64eaf97

How to cite

CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition — arXiv:2610.27901 — arXiv (en), https://arxiv.org/abs/2610.27901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f674a64eaf97 (Metraipolis archive dc_f674a64eaf97, sha256 cedc220ae1255b1afccd3477afebde13ae65df8305a31746932c3bf79412a192)
BibTeX
@misc{dcf674a64eaf97,
  title = {CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition — arXiv:2610.27901},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27901},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f674a64eaf97; sha256 cedc220ae1255b1afccd3477afebde13ae65df8305a31746932c3bf79412a192},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn interactions. In this setting, a useful assistant must be accurate, methodologically justified, logically consistent, and token-efficient. Current alignment approaches rarely achieve all of these together. Instruction-tuned models gain conversational quality through verbosity, and we show that science-agnostic general collaborative rewards compress responses at the expense of scientific rigor. We propose CollabSciReM, a goal-conditioned reward framework that decomposes the session-level reward into conversational quality, scientific rigor, and structural efficiency. We also introduce SciQuality, a pairwise evaluation of multi-turn research conversations grounded in 300 held-out scientific papers and scored on six dimensions: methodological soundness, justification, logical consistency, factual correctness, novelty, and responsiveness. Fine-tuned on 8.62K synthetic research conversations, CollabSciReM is preferred on SciQuality over a science-agnostic reward baseline trained on the same data for all four Llama and Qwen models, including a 65.3% win rate at matched response length. For the 7B and 8B models, CollabSciReM outperforms the science-agnostic reward baseline on the primary metric in 8 of 10 single- and multi-turn benchmark settings. In a blind study, domain experts rated CollabSciReM significantly higher on novelty than the general-reward variant and reported fewer hallucinated responses than both the general-reward variant and the base model.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.27901 — 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 2026-10-21T07:05:43.607Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).