In human conversation, both interlocutors play an active role in maintaining mutual understanding. When listeners are uncertain about what speakers mean, for example, they can request clarification. It is an open question for language models whether they can assume a similar listener role, recognizing and expressing their own uncertainty through clarification. We argue that reference games are a suitable testbed to approach this question as they are controlled, self-contained, and make clarification needs explicit and measurable. To test this, we evaluate three vision-language models comparing a baseline reference resolution task to an experiment where the models are instructed to request clarification when uncertain. The results suggest that even in such simple tasks, models often struggle to recognize internal uncertainty and translate it into adequate clarification behavior. This demonstrates the value of reference games as testbeds for interaction qualities of (vision and) language models.

We describe the GHADAI approach to the AraGenre 2026 shared task, which requires classifying Arabic text into broad and specific genre categories, including specific genres unseen during training. Our approach is a two-stage pipeline: a fine-tuned multilingual bi-encoder scores all 27,972 test sentences against the 74 candidate definitions, and a large language model reranks the top candidates per sentence using cyclic option rotation to mitigate positional bias. On the hidden test set, the bi-encoder achieves a hierarchical macro-F1 of 0.4213, which increases to 0.5006 with Fanar-9B reranking and to 0.6050 with Qwen-32B reranking over the top 15 candidates using five rotations. The final pipeline ranked fourth on the official leaderboard. These results demonstrate the effectiveness of combining definition-based retrieval with LLM reranking for generalization to unseen Arabic text genres.

Metaphor research has gained increasing attention due to its relevance to linguistic creativity, language use, cognitive processes, and related areas. While many efforts have been devoted to metaphor identification and annotation in English and other languages, Arabic remains under-resourced in this area. In this work, we propose the Arabic Metaphor Identification Procedure (AraMIP), a novel guideline for Arabic metaphor annotation. AraMIP builds on the widely used Metaphor Identification Procedure Vrije Universiteit (MIPVU) framework, incorporating adaptations that account for the language-specific properties of Arabic. We distinguish three major types of Arabic figurative language: isti‘āra (metaphor), kināya (metonymy/indirect expression), and tashbīh (simile) and annotate a pilot dataset of 300 sentences (5277 words). Our analysis reveals key challenges specific to Arabic, including morphological complexity, inconsistencies in dictionary sense ordering, and the absence of standardized contextual materials for annotators. This work contributes a first step toward standardized Arabic figurative instances and facilitates the development of larger annotated resources, thereby supporting future research on figurative language in Arabic.

We investigate the linguistic abilities of multimodal large language models in reference resolution tasks featuring simple yet abstract visual stimuli, such as color patches and color grids. Although the task may not seem challenging for today’s language models, being straightforward for human dyads, we consider it to be a highly relevant probe of the pragmatic capabilities of MLLMs. Our results and analyses indeed suggest that basic pragmatic capabilities, such as context-dependent interpretation of color descriptions, still constitute major challenges for state-of-the-art MLLMs.

Referring Expression Generation (REG) has a long-standing tradition in computational linguistics, and often aims to develop cognitively plausible models of language generation and dialogue modeling, in a multimodal context. Traditional approaches to reference have been mostly symbolic, recent ones have been mostly neural. Inspired by the recent interest in neuro-symbolic approaches in both fields – language and vision – we revisit REG from these perspectives. We review relevant neuro-symbolic approaches to language generation on the one hand and vision on the other hand, exploring possible future directions for cognitively plausible models of reference generation/reference game modeling.

We investigate whether pre-training exclusively on dialogue data results in formally and functionally apt small language models. Based on this pre-trained llamalogue model, we employ a variety of fine-tuning strategies to enforce “more communicative” text generations by our models. Although our models underperform on most standard BabyLM benchmarks, they excel at dialogue continuation prediction in a minimal pair setting. While PPO fine-tuning has mixed to adversarial effects on our models, DPO fine-tuning further improves their performance on our custom dialogue benchmark.