# Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

arXiv: https://arxiv.org/abs/2504.16060 · HTML: https://mlsanity.com/paper/2504.16060/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 55 of its 98 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 55)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [Large-scale interactive object segmentation with human annotators](https://mlsanity.com/paper/1903.10830/) (2019)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)

## Built on by (most cited first, 8 of 8)

- [Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models](https://mlsanity.com/paper/2510.04764/) (2025)
- [On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts](https://mlsanity.com/paper/2509.06952/) (2025)
- [Comprehension of Multilingual Expressions Referring to Target Objects in Visual Inputs](https://mlsanity.com/paper/2511.11427/) (2025)
- [Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps](https://mlsanity.com/paper/2510.23340/) (2025)
- [Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry](https://mlsanity.com/paper/2607.11053/) (2026)
- [ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement](https://mlsanity.com/paper/2608.16011/) (2026)
- [Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretation](https://mlsanity.com/paper/2608.29571/) (2026)
- [Learning to Refer from Estimated Listener Gaze](https://mlsanity.com/paper/2609.14207/) (2026)

## Abstract (arXiv)

Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative communication (Grice, 1975). However, current evaluations of vision-language models (VLMs) often overlook the pragmatic dimension, reducing REG to a region-based captioning task and neglecting Gricean maxims. In this work, we revisit REG from a pragmatic perspective, introducing a new dataset (RefOI) of 1.5k images annotated with both written and spoken referring expressions. Through a systematic evaluation of state-of-the-art VLMs, we identify three key failures of pragmatic competence: (1) failure to uniquely identify the referent, (2) inclusion of excessive or irrelevant information, and (3) misalignment with human pragmatic preference, such as the underuse of minimal spatial cues. We also show that standard automatic evaluations fail to capture these pragmatic violations, reinforcing superficial cues rather than genuine referential success. Our findings call for a renewed focus on pragmatically informed models and evaluation frameworks that align with real human communication.