作者位次 #2/4ACL 2026Findings· Findings of ACL
What Tokens Truly Matter? The Logit Conflation Problem in LLM Sampling
Pinlong Zhao · Huijun Tang · Pengfei Jiao · Mengyang Li
摘要
Sampling methods for large language models select candidate tokens based on logit statistics, implicitly assuming that high logits indicate desirable outputs. We identify the Logit Conflation Problem, where a token’s logit aggregates prompt-independent factors, including linguistic fluency and pa...