{"paper":{"title":"Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations.","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chris North, Eric Krokos, Ibrahim Tahmid, Kirsten Whitley, Xuan Wang, Xuxin Tang","submitted_at":"2026-04-21T20:28:42Z","abstract_excerpt":"Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study (N=14) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs can accurately perceive semantic interactions from spatial layouts and reason about refinement intent without persistent human-LLM misalignment, as assumed in the framework design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Semantic Prompting enables LLMs to perform precise incremental narrative revisions by perceiving semantic interactions in spatial layouts, addressing misalignment gaps in existing methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5beb05b4297fd0433e914e23cf974c05800cd1d29907ee591d3e64ba5a1b2e9d"},"source":{"id":"2604.19971","kind":"arxiv","version":2},"verdict":{"id":"baca82a1-7d05-4d81-9805-542231646bf6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T01:16:43.451059Z","strongest_claim":"The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study (N=14) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering.","one_line_summary":"Semantic Prompting enables LLMs to perform precise incremental narrative revisions by perceiving semantic interactions in spatial layouts, addressing misalignment gaps in existing methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs can accurately perceive semantic interactions from spatial layouts and reason about refinement intent without persistent human-LLM misalignment, as assumed in the framework design.","pith_extraction_headline":"Semantic Prompting lets LLMs interpret spatial layout changes to make targeted narrative revisions instead of full regenerations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19971/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T15:39:46.206286Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:29:52.385944Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"06055c0717c1156dfb2ae7c31de476b6a32b64051fd4d33d614339fe3a8fd05c"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}