Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference
Not on the map. Why?
Abstract (arXiv)
Our goal is to study how LLMs represent and interpret plural reference in ambiguous and unambiguous contexts. We ask the following research questions: (1) Do LLMs exhibit human-like preferences in representing plural reference? (2) Are LLMs able to detect ambiguity in plural anaphoric expressions and identify possible referents? To address these questions, we design a set of experiments, examining pronoun production using next-token prediction tasks, pronoun interpretation, and ambiguity detection using different prompting strategies. We then assess how comparable LLMs are to humans in formulating and interpreting plural reference. We find that LLMs are sometimes aware of possible referents of ambiguous pronouns. However, they do not always follow human reference when choosing between interpretations, especially when the possible interpretation is not explicitly mentioned. In addition, they struggle to identify ambiguity without direct instruction. Our findings also reveal inconsistencies in the results across different types of experiments.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 6 Oct 2025.
Builds on
11 of 33 references.
References · 11
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2017End-to-end Neural Coreference Resolutioncited by 240
- 2023Attribution Patching Outperforms Automated Circuit Discoverycited by 196
- 2023We're Afraid Language Models Aren't Modeling Ambiguitycited by 124
- 2022Coreference Resolution through a seq2seq Transition-Based Systemcited by 34
- 2023Zero and Few-shot Semantic Parsing with Ambiguous Inputscited by 16
- 2024To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguitycited by 8
- 2020Free the Plural: Unrestricted Split-Antecedent Anaphora Resolutioncited by 7
- 2024Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!cited by 7
- 2024Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Modelscited by 4
- 2025Trick or Neat: Adversarial Ambiguity and Language Model Evaluationcited by 3
Built on by
Not cited yet.