# How Much Do LLMs Know About Chinese Zero Pronouns?

arXiv: https://arxiv.org/abs/2605.31056 · HTML: https://mlsanity.com/paper/2605.31056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 12 of 12)

- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [GPTEval: A Survey on Assessments of ChatGPT and GPT-4](https://mlsanity.com/paper/2308.12488/) (2023)
- [Large Language Models Pass the Turing Test](https://mlsanity.com/paper/2503.23674/) (2025)
- [Are Large Language Models Robust Coreference Resolvers?](https://mlsanity.com/paper/2305.14489/) (2023)
- [Translating Pro-Drop Languages with Reconstruction Models](https://mlsanity.com/paper/1801.03257/) (2018)
- [One Model to Learn Both: Zero Pronoun Prediction and Translation](https://mlsanity.com/paper/1909.00369/) (2019)
- [A Survey on Zero Pronoun Translation](https://mlsanity.com/paper/2305.10196/) (2023)
- [Deep Reinforcement Learning for Chinese Zero pronoun Resolution](https://mlsanity.com/paper/1806.03711/) (2018)
- [Neural Recovery Machine for Chinese Dropped Pronoun](https://mlsanity.com/paper/1605.02134/) (2016)
- [Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution](https://mlsanity.com/paper/2104.07425/) (2021)
- [A Survey on Semantic Processing Techniques](https://mlsanity.com/paper/2310.18345/) (2023)
- [Evaluating the Translation Performance of Large Language Models Based on Euas-20](https://mlsanity.com/paper/2408.03119/) (2024)

## Abstract (arXiv)

Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and have long posed a challenge for natural language processing systems. Although Large Language Models (LLMs) perform well on many Chinese language tasks, their ability to process ZPs remains poorly understood. We conduct a systematic investigation of LLMs' handling of Chinese ZPs through a sequence of linguistically motivated tasks, including identification, referentiality classification, referential type classification, resolution, and translation. A diverse set of LLMs is evaluated across all tasks. Our results show that Chinese ZPs remain highly challenging for current LLMs, particularly for upstream tasks such as identification and referentiality classification. Performance on downstream tasks, such as ZP translation, is also consistently low: even state-of-the-art reasoning-oriented LLMs correctly translate fewer than half of Chinese ZPs into English.