Evaluating LLMs on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)

Xiaodong Yang
4/21/2025
cs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This paper proposes a framework for evaluating large language models (LLMs) on Chinese topic constructions, focusing on their sensitivity to island constraints. Drawing inspiration from Tian et al. (2024), we outline an experimental design for testing LLMs' grammatical knowledge of Mandarin syntax. While no experiments have been conducted yet, this proposal aims to provide a foundation for future studies and invites feedback on the methodology.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Measuring Taiwanese Mandarin Language Understanding

87% match2024

FoundaBench: Evaluating Chinese Fundamental Knowledge Capabilities of Large Language Models

85% match2024

LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models

84% match2024

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models

84% match2024

Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model

84% match2024

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models

84% match2024

Cite this paper

@article{yang2025evaluating,
  title  = {Evaluating LLMs on Chinese Topic Constructions: A Research Proposal Inspired by Tian et al. (2024)},
  author = {Xiaodong Yang},
  year   = {2025},
  eprint = {2504.14969},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.14969v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.14969.svg)](https://codeofpaper.com/paper/2504.14969)

Discussion