# Language Models at the Syntax-Semantics Interface: A Case Study of the Long-Distance Binding of Chinese Reflexive ziji

arXiv: https://arxiv.org/abs/2504.02116 · HTML: https://mlsanity.com/paper/2504.02116/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 68 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://mlsanity.com/paper/1809.00042/) (2018)
- [Testing the Predictions of Surprisal Theory in 11 Languages](https://mlsanity.com/paper/2307.03667/) (2023)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [UER: An Open-Source Toolkit for Pre-training Models](https://mlsanity.com/paper/1909.05658/) (2019)
- [Frequency Effects on Syntactic Rule Learning in Transformers](https://mlsanity.com/paper/2109.07020/) (2021)
- [CLiMP: A Benchmark for Chinese Language Model Evaluation](https://mlsanity.com/paper/2101.11131/) (2021)
- [Testing AI on language comprehension tasks reveals insensitivity to underlying meaning](https://mlsanity.com/paper/2302.12313/) (2023)
- [Refining Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/2104.09635/) (2021)
- [CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model](https://mlsanity.com/paper/2003.01355/) (2020)
- [Language Models Use Monotonicity to Assess NPI Licensing](https://mlsanity.com/paper/2105.13818/) (2021)
- [Do Neural Language Models Show Preferences for Syntactic Formalisms?](https://mlsanity.com/paper/2004.14096/) (2020)
- [PERT: Pre-training BERT with Permuted Language Model](https://mlsanity.com/paper/2203.06906/) (2022)
- [TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities](https://mlsanity.com/paper/2212.06385/) (2022)
- [SLING: Sino Linguistic Evaluation of Large Language Models](https://mlsanity.com/paper/2210.11689/) (2022)
- [LLM Cognitive Judgements Differ From Human](https://mlsanity.com/paper/2307.11787/) (2023)

## Built on by (most cited first, 2 of 2)

- [Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements](https://mlsanity.com/paper/2506.01089/) (2025)
- [Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions](https://mlsanity.com/paper/2605.31586/) (2026)

## Abstract (arXiv)

This paper explores whether language models can effectively resolve the complex binding patterns of the Mandarin Chinese reflexive ziji, which are constrained by both syntactic and semantic factors. We construct a dataset of 240 synthetic sentences using templates and examples from syntactic literature, along with 320 natural sentences from the BCC corpus. Evaluating 21 language models against this dataset and comparing their performance to judgments from native Mandarin speakers, we find that none of the models consistently replicates human-like judgments. The results indicate that existing language models tend to rely heavily on sequential cues, though not always favoring the closest strings, and often overlooking subtle semantic and syntactic constraints. They tend to be more sensitive to noun-related than verb-related semantics.