# Evaluating Chinese Ambiguity Understanding in Large Language Models

arXiv: https://arxiv.org/abs/2605.15635 · HTML: https://mlsanity.com/paper/2605.15635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models](https://mlsanity.com/paper/2305.13711/) (2023)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias](https://mlsanity.com/paper/2308.00225/) (2023)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [Linguistic ambiguity analysis in ChatGPT](https://mlsanity.com/paper/2302.06426/) (2023)
- [Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions](https://mlsanity.com/paper/2412.08169/) (2024)
- [The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation](https://mlsanity.com/paper/2503.03308/) (2025)
- [3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset](https://mlsanity.com/paper/2404.18413/) (2024)
- [MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models](https://mlsanity.com/paper/2506.17046/) (2025)
- [Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity](https://mlsanity.com/paper/2507.23121/) (2025)

## Abstract (arXiv)

Linguistic ambiguity is critical to the robustness of Large Language Models (LLMs), yet existing research focuses mostly on English, with limited attention devoted to Chinese. Existing Chinese ambiguity datasets (e.g., CHAmbi) suffer from poor scalability. Guided by Potential Ambiguity (PA) Theory, we design a semi-automatic pipeline to construct CHA-Gen. It is the first PA Theory-grounded Chinese ambiguity dataset, which comprises 5,712 sentences (2,414 ambiguous, 3,298 unambiguous) across 18 potential ambiguous structures. Evaluating LLMs (e.g. Gemma 3, Qwen 2.5/3 series) via direct querying and machine translation, we find that LLMs struggle with ambiguity detection (improved by CoT prompting). Analysis of Qwen3-32B's CoT rationales reveals three common failure modes: ambiguity blindness, misattribution, and premature resolution. Uncertainty quantification with semantic entropy metric shows higher uncertainty for ambiguous sentences. Moreover, instruction tuning induces overconfidence, whereas Base models better capture semantic diversity. We further observe that models exhibit a bias toward dominant interpretations. Our work provides a scalable approach for Chinese ambiguity corpus and insights into LLMs' ambiguity handling, laying a foundation for enhancing Chinese ambiguity research in LLMs.