Skip to yearly menu bar Skip to main content

Workshop: Instruction Tuning and Instruction Following

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

Seonghyeon Ye · Doyoung Kim · Sungdong Kim · Hyeonbin Hwang · Seungone Kim · Yongrae Jo · James Thorne · Juho Kim · Minjoon Seo

Keywords: [ language model evaluation ] [ Large language models ] [ Natural Language Processing ]


Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on the instruction. However, previous studies have mainly focused on coarse-grained evaluation (i.e. overall preference-based evaluation), which limits interpretability since it does not consider the nature of user instructions that require instance-wise skill composition. In this paper, we introduce FLASK (Fine-grained Language Model Evaluation based on Alignment Skill Sets), a fine-grained evaluation protocol for both human-based and model-based evaluation which decomposes coarse-level scoring to a skill set-level scoring for each instruction. We experimentally observe that the fine-graininess of evaluation is crucial for attaining a holistic view of model performance and increasing the reliability of the evaluation. Using FLASK, we compare multiple open-source and proprietary LLMs and observe a high correlation between model-based and human-based evaluations.

Chat is not available.