
AL
Austin LaHue, Michael Burr, Luis David Garcia Puente, Vinita Gangaram Jansari, Benjamin Nye, Carlos Toxtli Hernandez
· 1 min read
ResearcharXiv cs.CL
Which Mathematical Context Supports Target-Aligned Conjecture Generation? A Paired Ablation Study
arXiv:2611.18621v1 Announce Type: new
Abstract: Generating mathematical conjectures from natural-language context is challenging because theorem-relevant information is distributed across multiple forms of mathematical context, including definitions, objects, assumptions, and constructions. We study which of these contextual signals help a model recover the specific claim supported by the surrounding setup, using 61 main theorems from 12 papers across four mathematical domains. For each theorem, we redact the result and represent the remaining setup using six context components. A paired ablation design compares full context, six leave-one-out conditions, and six single-component conditions, yielding 793 generated conjectures. Context components were largely complementary: removing one component usually had little effect, whereas retaining only one substantially reduced expected-theorem alignment. Local Mathematical Objects provided the strongest standalone signal, while Structural Constraints and Conditions produced the largest alignment decrease when removed. These findings suggest that target-aligned conjecture generation depends on combining information that identifies relevant objects with information that constrains admissible claims.
Original source
This story was published by arXiv cs.CL and written by Austin LaHue, Michael Burr, Luis David Garcia Puente, Vinita Gangaram Jansari, Benjamin Nye, Carlos Toxtli Hernandez. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


