FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models
This addresses the need for better evaluation benchmarks for LLMs, though it is incremental as it builds on existing work by adding multi-language and human-crafted aspects.
The authors tackled the problem of assessing instruction-following in large language models by introducing FollowEval, a multi-dimensional benchmark in English and Chinese with human-crafted examples, and found that LLM performance significantly lags behind humans.
The effective assessment of the instruction-following ability of large language models (LLMs) is of paramount importance. A model that cannot adhere to human instructions might be not able to provide reliable and helpful responses. In pursuit of this goal, various benchmarks have been constructed to evaluate the instruction-following capacity of these models. However, these benchmarks are limited to a single language and are constructed using automated approaches, which restricts their applicability and the quality of the test examples they contain. To bridge this gap, we introduce the FollowEval benchmark in this paper. This benchmark is composed of instances in both English and Chinese, and all test examples are crafted by human experts. Furthermore, the FollowEval benchmark is designed to assess LLMs across five critical dimensions of instruction following: string manipulation, commonsense reasoning, logical reasoning, spatial reasoning, and response constraints. To enhance the complexity and present a sufficient challenge, each test example is designed to evaluate more than one dimension. We have evaluated various LLMs using the FollowEval benchmark and found that their performance significantly lags behind that of humans. This highlights the considerable room for improvement in the instruction-following ability of these models.