SOURCE-LINKED INTELLIGENCE

Not What You Meant: Can LLMs Follow a Specified Negation Semantics?

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force -- open- versus closed-world, two- versus three-valued, and credulous versus skeptical. We study which reading of negation large language models adopt by default and whether they can override that preference when a different reading is explicitly specified. To this end, we introduce NAFBench, a procedural generator of solver-certified instances spanning four semantic viewpoints: SLDNF, well-founded semantics (WFS), and credulo

Read original source ↗ Open in workspace

recordType

paper

region

Global