Next-ToBE: Enabling Overconfident LLMs to See Further and Reason More Accurately

The ICLR 2026 paper introduces Next‑ToBE, a training‑objective modification that replaces the one‑hot next‑token label with a soft distribution over a future token window, unlocking latent foresight in LLMs, improving future‑token hit rate, downstream reasoning performance, and reducing training memory and time.

Future Token PredictionLarge Language ModelsNext-ToBE

0 likes · 12 min read

Next-ToBE: Enabling Overconfident LLMs to See Further and Reason More Accurately

Machine Learning Algorithms & Natural Language Processing

May 21, 2026 · Artificial Intelligence

Can a New Training Objective Make LLMs See Further and Reason Better?

The paper introduces Next‑ToBE, a training‑objective modification that replaces the one‑hot next‑token label with a soft distribution covering a future token window, thereby activating latent anticipatory capacity in large language models and yielding significant gains in token‑hit rates, reasoning accuracy, and training efficiency.

Anticipatory CapacityLarge Language ModelsNext-ToBE

0 likes · 11 min read

Can a New Training Objective Make LLMs See Further and Reason Better?