Year: 2026
Type: conference-paper
Abstract: 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 parametric associations, with prompt-relevance.However, only prompt-relevance determines instruction-following quality.We propose SEAL-Sampling (Signal Extraction for Active ReLevance) to isolate this component through attention-weighted attribution.Our framework defines prompt-relevance as the causal effect of prompt content on token logits and establishes attention patterns as an efficient proxy.Experiments on LLaMA-3 demonstrate significant improvements over top-nσ, with gains of 1.8% on AlpacaEval 2.0 and 2.2% on IFEval.Furthermore, attribution scores correlate weakly with raw logits, confirming the extraction of an orthogonal signal.The method is training-free and introduces minimal latency, adding less than 12ms overhead per token.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166808837