XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates

Haopeng Zhang, Hayate Iso, Sairam Gurajada, Nikita Bhutani


Abstract
Text editing is a crucial task of modifying text to better align with user intents. However, existing text editing benchmark datasets contain only coarse-grained instructions and lack explainability, thus resulting in outputs that deviate from the intended changes outlined in the gold reference. To comprehensively investigate the text editing capabilities of large language models (LLMs), this paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing. XATU considers finer-grained text editing tasks of varying difficulty (simplification, grammar check, fact-check, etc.), incorporating lexical, syntactic, semantic, and knowledge-intensive edit aspects. To enhance interpretability, we combine LLM-based annotation and human annotation, resulting in a benchmark that includes fine-grained instructions and gold-standard edit explanations. By evaluating existing LLMs against our benchmark, we demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks. Furthermore, extensive experimentation reveals the significant role of explanations in fine-tuning language models for text editing tasks. The benchmark will be open-sourced to support reproduction and facilitate future research at https://github.com/megagonlabs/xatu.
Anthology ID:
2024.lrec-main.1543
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
17739–17752
Language:
URL:
https://aclanthology.org/2024.lrec-main.1543
DOI:
Bibkey:
Cite (ACL):
Haopeng Zhang, Hayate Iso, Sairam Gurajada, and Nikita Bhutani. 2024. XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17739–17752, Torino, Italia. ELRA and ICCL.
Cite (Informal):
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates (Zhang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1543.pdf