AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
New York University
AskChem restructures chemistry literature search around 2.4 million individually verifiable claims extracted from 147,000 papers, organized via a faceted taxonomy and an evidence graph linking related findings across publications.
Why it matters
Grounding an LLM's responses through AskChem raised resolvable-citation accuracy from 88.3% to 100%, a concrete fix for one of the biggest reliability gaps in LLM-assisted literature synthesis.
Importance: 3/5
Notable research release with a concrete reliability improvement (88.3% to 100% resolvable-citation accuracy).
Sources
official
AskChem (arXiv)