👻 Hallucination Detection

🧠 NeurIPS2026 · 1 paper notes

📌 Same area in other venues: 🎞️ ECCV2026 (20) · 📷 CVPR2026 (33) · 🔬 ICLR2026 (40) · 💬 ACL2026 (28) · 🧪 ICML2026 (21) · 🤖 AAAI2026 (15)

The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining

The paper localises a sparse Commit-Abstain Circuit (CAC) using the pre-generation commit–abstain logit margin, identifies early commitment accumulation with insufficient late abstention correction, and trains a lightweight policy on component contributions that raises reported mean decision accuracy from 0.692 to 0.814, rather than demonstrating improved answer-content accuracy.