Towards explainable language reasoning via multi-modal knowledge graphs
Chunyu Lu, Jun Luo, Kang Yu, Tianran Chen, Xueli Wang, Feng Qian, Chen Xi · 2026
Read Towards explainable language reasoning via multi-modal knowledge graphs by Chunyu Lu, Jun Luo, Kang Yu, Tianran Chen, Xueli Wang, Feng Qian, Chen Xi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13350891.txt.
Description
Chunyu Lu and co-authors build a reasoning system that shows its work. Large language models reason well but hide their paths. That opacity is a problem in high-stakes settings. The team's design grounds each step in a multi-modal knowledge graph. Text, images and structure share one graph form.
A planner-executor split runs the show. The language model drafts a plan in strict symbolic form. A fixed graph engine then carries it out. The engine returns an answer plus the exact subgraph behind it, ready to replay. Scores on six benchmarks stayed competitive. The authors stress the audit trail as the main gain, and they state plainly what their claims on faithfulness can and cannot cover.
Catalog record
| CREATOR | Chunyu Lu, Jun Luo, Kang Yu, Tianran Chen, Xueli Wang, Feng Qian, Chen Xi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |