Fact-Anchored Split Reasoning
Year: 2026
Type: preprint
Abstract: We propose Fact-Anchored Split Reasoning (FASR), a layered NLParchitecture that improves machine reasoning on semantically contradictory andcomplex sentences. Unlike conventional transformer models that process fullsentences as a single unit, FASR first detects a known fact anchor embedded inthe input — a clause whose truth is supported by the model's training knowledge— then splits the sentence into two parts at that anchor point. Each partindependently retrieves a concept set, after which a bridging layer identifies theshared conceptual medium connecting both parts, and a reasoning chain isconstructed toward a conclusion. Experiments on five contradictorycommonsense sentences demonstrate that FASR achieves a mean semanticalignment score of 0.6387 against expected reasoning links, compared to abaseline score of 0.4628 — a 38.0% relative improvement — winning all fivetest cases (5–0).
Author: Jha, Ayushman
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7221473876
Cites:
Cited by:
Related to: