AI RESEARCH
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
arXiv CS.LG
•
ArXi:2603.18482v1 Announce Type: cross Standard decoding strategies for text generation, including top-k, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting selection to high-probability regions. Human language production operates differently: tokens are chosen for communicative appropriateness rather than statistical frequency. This mismatch creates a truncation blind spot: contextually appropriate but statistically rare tokens remain accessible to humans yet unreachable by likelihood-based decoding.