How XTC Works: Probabilistically Excluding Top Token Choices to Boost Diversity
ziv_ravid · x · 2026-09-26
XTC (Exclude Top Choices) mechanism: when two or more tokens clear a probability threshold τ, with probability ρ it removes all of them except the least likely one and renormalizes. When the model is confident, it does nothing.
It deliberately excludes the most generic head tokens precisely when several continuations are equally plausible, forcing more diverse outputs.
More from Research
- Absolute Zero Reasoner revisited: self-play reasoning with zero external data and its 'uh-oh' moment — cephaloform · 2026-09-26
- Should Double-Blind Peer Review Be Replaced by Fully Open Review in the AI Era? — Temporary_Switch_339 · 2026-09-26
- Jev-Mem: System-One/Two-Inspired Memory Architecture Builds Agent Memory 6.6x Faster — omarsar0 · 2026-09-26
- Stanford paper on boosting LLM creativity via cross-domain analogy accepted at NeurIPS 2026 — james_y_zou · 2026-09-26
- Aran Nayebi: AI agents can't self-generate goals yet, but most other limits are engineering problems — aran_nayebi · 2026-09-26
- New competition platform pits tiny neural networks under 800 parameters at strategy games — codetiger42 · 2026-09-26