X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects

arXiv:2311.08788v2 Announce Type: replace-cross
Abstract: Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate the text in both seen and unseen aspects customized by end users. X-Eval consists of two …

abstract arxiv assessment cs.ai cs.cl cs.lg evaluation generated however language language generation natural natural language natural language generation nlg text type via