Evidence Paths: Grounding LLM-Generated Hypotheses in Semantic Web Knowledge GraphsScientific discovery depends on connecting claims scattered across a fragmented literature—yet researchers’ tools offer either creative breadth or rigorous traceability, rarely both.
doi
10.1145/3800935.3830863
isbn
979-8-4007-2564-7
name
Evidence Paths: Grounding LLM-Generated Hypotheses in Semantic Web Knowledge Graphs
source
html
acm_url
https://dl.acm.org/doi/10.1145/3800935.3830863
authors
Nicola Raffaele Di Matteo, James Blustein
doi_url
https://doi.org/10.1145/3800935.3830863
license
CC BY 4.0
summary
Scientific discovery depends on connecting claims scattered across a fragmented literature—yet researchers’ tools offer either creative breadth or rigorous traceability, rarely both.
keywords
Semantic Web; large language models; literature-based discovery; knowledge graphs; nanopublications; human in the loop
published
2026-09-14
conference
HT '26: 37th ACM Conference on Hypertext, London, United Kingdom, September 14–18, 2026
acm_html_url
https://dl.acm.org/doi/fullHtml/10.1145/3800935.3830863
ccs_concepts
CCS Concepts: • Theory of computation → Automated reasoning ; • Computing methodologies → Discourse, dialogue and pragmatics ; • Human-centered computing → Hypertext / hypermedia ; • Human-centered computing → Collaborative interaction ; • Information systems → Web searching and information discovery ;
displayAuthor
Nicola Raffaele Di Matteo, James Blustein
proceedings_url
https://dl.acm.org/doi/proceedings/10.1145/3800935
displayPublishTime
2026-09-14
acm_reference_format
ACM Reference Format: Nicola Raffaele Di Matteo and James Blustein. 2026. Evidence Paths: Grounding LLM-Generated Hypotheses in Semantic Web Knowledge Graphs. In 37th ACM Conference on Hypertext (HT '26), September 14--18, 2026, London, United Kingdom. ACM, New York, NY, USA 7 Pages. https://doi.org/10.1145/3800935.3830863