Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation
This addresses the lack of evaluation metrics for instruction-following in LLMs, which is an incremental improvement for researchers and developers in natural language processing.
The paper tackles the problem of evaluating instruction-following ability in large language models for story-ending generation, proposing an automatic evaluation pipeline using a machine reading comprehension model, and finds that it aligns with human evaluation and shows open-source LLMs can perform close to GPT-3.5.
Instruction-tuned Large Language Models (LLMs) have achieved remarkable performance across various benchmark tasks. While providing instructions to LLMs for guiding their generations is user-friendly, assessing their instruction-following capabilities is still unclarified due to a lack of evaluation metrics. In this paper, we focus on evaluating the instruction-following ability of LLMs in the context of story-ending generation, which requires diverse and context-specific instructions. We propose an automatic evaluation pipeline that utilizes a machine reading comprehension (MRC) model to determine whether the generated story-ending reflects instruction. Our findings demonstrate that our proposed metric aligns with human evaluation. Furthermore, our experiments confirm that recent open-source LLMs can achieve instruction-following performance close to GPT-3.5, as assessed through automatic evaluation.