Using generalized stochastic dominance, the authors find that human-written text completions are not significantly outperformed by five LLM decoding strategies across mixed cardinal and ordinal quality metrics.
A Statistical Case Against Empirical Human-AI Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introduce statistical biases that warrant caution. This position paper thus advocates against naive empirical alignment, offering prescriptive alignment and a posteriori empirical alignment as alternatives. We substantiate our principled argument by tangible examples like human-centric decoding of language models.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Statistical Multicriteria Evaluation of LLM-Generated Text
Using generalized stochastic dominance, the authors find that human-written text completions are not significantly outperformed by five LLM decoding strategies across mixed cardinal and ordinal quality metrics.