# Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion

arXiv: https://arxiv.org/abs/2306.03055 · HTML: https://mlsanity.com/paper/2306.03055/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 11 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 2 of 2)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)

## Built on by (most cited first, 1 of 1)

- [Polite on the Surface, Broken in Practice: A Curated Dataset for Fixing Generation and Register Failures in Low-Resource Bangla Text Generation](https://mlsanity.com/paper/2605.22487/) (2026)

## Abstract (arXiv)

Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can flexibly handle Japanese honorifics like humans. To analyze this, we introduce an honorific conversion task that considers social relationships among people mentioned in a conversation. We construct a Japanese honorifics dataset from problem templates of various sentence structures to investigate the syntactic generalization capacity of GPT-3, one of the leading LLMs, on this task under two settings: fine-tuning and prompt learning. Our results showed that the fine-tuned GPT-3 performed better in a context-aware honorific conversion task than the prompt-based one. The fine-tuned model demonstrated overall syntactic generalizability towards compound honorific sentences, except when tested with the data involving direct speech.