1 citations · 1 across the 2 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case
Tingzhu Bi, Ping Wang, Meng Ma
Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is enough to close the case. We st…
cs.SE2026
JustDiag!: A Diagnostic Justification Engine for Accountable Root Cause Analysis
Tingzhu Bi, Xinrui Jiang, Xun Zhang +5
Large language models can produce fluent root cause analyses, but fluent final answers alone are insufficient evidence for accountability in high-stakes operations. In real inciden…