AResKGLM: a graph-grounded language-model framework for interpretable multi-hop antimicrobial resistance reasoning
Jie Ren, Ziyi Yang, Wei Liu, Man Tat Alexander Ng · 2026
Read AResKGLM: a graph-grounded language-model framework for interpretable multi-hop antimicrobial resistance reasoning by Jie Ren, Ziyi Yang, Wei Liu, Man Tat Alexander Ng (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-13537466.txt.
Description
Jie Ren and co-authors built AResKGLM, a 2026 system that reasons over knowledge graphs to rank the genes behind drug resistance in microbes. Resistance arises from webs of genes, mobile elements, and settings. Older graph tools crush that evidence into a single score, while plain language models explain without proof.
The system pulls multi-step paths from the graph and pairs them with short profiles of each entity. It feeds both to a tuned language model that answers with a prediction plus a short reasoning trace. On a standard benchmark it beat three rival graph methods, and its edge grew as reasoning chains lengthened. Tests across three major pathogens held up, and a time-based check ranked recent gene-drug links with high precision.
Catalog record
| CREATOR | Jie Ren, Ziyi Yang, Wei Liu, Man Tat Alexander Ng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |