2 papers
cs.CL2026
Pangram 4 Technical Report
Ben Glickenhaus, Katherine Thai, Jenna Russell +4
We present Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. We achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false…
cs.AI2026
STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
Xinkang Li, Rong Jiang, Xin Song +3
In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing metho…