# Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics

Source: [Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics](<https://www.sota2.com/research/paper/68fa6dc61e209131cea3c188>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:43:12.182Z

Authors: Elisa Kreiss, Cynthia Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts

Published: 2022-05-21T17:35:26.000Z

## Abstract

Few images on the Web receive alt-text descriptions that would make them accessible to blind and low vision (BLV) users. Image-based NLG systems have progressed to the point where they can begin to address this persistent societal problem, but these systems will not be fully successful unless we evaluate them on metrics that guide their development correctly. Here, we argue against current referenceless metrics -- those that don't rely on human-generated ground-truth descriptions -- on the grounds that they do not align with the needs of BLV users. The fundamental shortcoming of these metrics is that they do not take context into account, whereas contextual information is highly valued by BLV users. To substantiate these claims, we present a study with BLV participants who rated descriptions along a variety of dimensions. An in-depth analysis reveals that the lack of context-awareness makes current referenceless metrics inadequate for advancing image accessibility. As a proof-of-concept, we provide a contextual version of the referenceless metric CLIPScore which begins to address the disconnect to the BLV data. An accessible HTML version of this paper is available at https://elisakreiss.github.io/contextual-description-evaluation/paper/reflessmetrics.html

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multimodal Preference Evaluation on VL-GUIDEDATA-B](<https://www.sota2.com/research/sota/multimodal-preference-evaluation-on-vl-guidedata-b.md>): Multimodal Preference Evaluation; VL-GUIDEDATA-B; Kendall's Tau: -5.08.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2205.10646>)

[PDF](<https://arxiv.org/pdf/2205.10646.pdf>)
