ToxReason is an AOP-grounded benchmark that evaluates LLMs on mechanistic organ-level toxicity reasoning from molecular initiating events to adverse outcomes, showing that high predictive accuracy does not guarantee faithful biological explanations.
•Predicted Toxicity:Liver toxicity LLM-as-a-Judge Evaluation: Qwen-4B-Inst
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.QM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ToxReason: A Benchmark for Mechanistic Chemical Toxicity Reasoning via Adverse Outcome Pathway
ToxReason is an AOP-grounded benchmark that evaluates LLMs on mechanistic organ-level toxicity reasoning from molecular initiating events to adverse outcomes, showing that high predictive accuracy does not guarantee faithful biological explanations.