Vision-language models (VLMs) are increasingly used to make visual content accessible via text-based descriptions. In current systems, however, description specificity is often conflated with their length. We argue that these two concepts must be disentangled: descriptions can be concise yet dense with information, or lengthy yet vacuous. We define specificity relative to a contrast set, where a description is more specific to the extent that it picks out the target image better than other possible images. We construct a dataset that controls for length while varying information content, and validate that people reliably prefer more specific descriptions regardless of length. We find that controlling for length alone cannot account for differences in specificity; it matters how the length budget is applied. These results support evaluation approaches that directly prioritize specificity over verbosity.

Image description generation models are sophisticated Vision-Language Models which promise to make visual content, such as images, non-visually accessible through linguistic descriptions. While these systems can benefit all, their primary motivation tends to lie in allowing blind and low-vision (BLV) users access to increasingly visual (online) discourse. Well-defined evaluation methods are crucial for steering model development into socially useful directions. In this work, we show that the most popular evaluation metrics (reference-based metrics) are biased against BLV users and therefore potentially stifle useful model development. Reference-based metrics assign quality scores based on the similarity to human-generated ground-truth descriptions and are widely accepted as neutrally representing the needs of all users. However, we find that these metrics are more strongly correlated with sighted participant ratings than BLV ratings, and we explore factors which appear to mediate this finding: description length, the image’s context of appearance, and the number of reference descriptions available. These findings suggest that there is a need for developing evaluation methods that are established based on specific downstream user groups, and they highlight the importance of reflecting on emerging biases against minorities in the development of general-purpose automatic metrics.

Recent, innovative efforts to understand the uneven distribution of languages and linguistic feature values in time and space attest to both the challenge these issues pose and the value in solving them. In this paper, we introduce a model for simulating languages and their features over time in a realistic geographic environment. At its core is a model of language phylogeny and migration whose parameters are chosen to reproduce known language family sizes and geographic dispersions. This foundation in turn is used to explore the dynamics of linguistic features. Languages are assigned feature values that can change randomly or under the influence of nearby languages according to predetermined probabilities. We assess the effects of these settings on resulting geographic and genealogical patterns using homogeneity measures defined in the literature. The resulting model is both flexible and realistic, and it can be employed to answer a wide range of related questions.