Prompting and steering techniques are well established in general-purpose generative AI, yet assistive visual question answering (VQA) tools for blind users still follow rigid interaction patterns with limited opportunities for customization. User control can be helpful when system responses are misaligned with their goals and contexts, a gap that becomes especially consequential for blind users that may rely on these systems for access. We invite 11 blind users to customize their interactions with a real-world conversational VQA system. Drawing on 418 interactions, reflections, and post-study interviews, we analyze prompting-based techniques participants adopted, including those introduced in the study and those developed independently in real-world settings. VQA interactions were often lengthy: participants averaged 3 turns, sometimes up to 21, with input text typically tenfold shorter than the responses they heard. Built on state-of-the-art LLMs, the system lacked verbosity controls, was limited in estimating distance in space and time, relied on inaccessible image framing, and offered little to no camera guidance. We discuss how customization techniques such as prompt engineering can help participants work around these limitations. Alongside a new publicly available dataset, we offer insights for interaction design at both query and system levels.

Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the semantics of the textual description, using Large Language Models (LLMs) to break them down into subsets of questions and answers. However, these methods primarily operate on the surface level, failing to incorporate deeper lexical understanding while introducing incorrect assumptions generated by the LLM. In response to these issues, we present Caption Expansion with Contradictions and Entailments (CECE), a principled approach that leverages Natural Language Inference (NLI) to generate entailments and contradictions from a given premise. CECE produces lexically diverse sentences while maintaining their core meaning. Through extensive experiments, we show that CECE enhances interpretability and reduces overreliance on biased or superficial features. By balancing CECE along the original premise, we achieve significant improvements over previous methods without requiring additional fine-tuning, producing state-of-the-art results on benchmarks that score agreement with human judgments for image-text alignment, and achieving an increase in performance on Winoground of $+19.2\%$ (group score) and $+12.9\%$ on EqBen (group score) over the best prior work (finetuned with targeted data).

This paper presents a longitudinal study investigating how the General Data Protection Regulation (GDPR) compliance of website privacy policies has evolved over a fiveyear period. Using an automated privacy policy evaluation tool, we assessed ten core GDPR factors across a corpus of websites originally analyzed in 2020 and re-evaluated in 2025. Our analysis reveals a mixed progression: while user-facing compliance measures such as consent, data retention notification, and data sharing transparency showed measurable improvement, technically oriented factors-such as breach notification and data encryption-experienced a decline in explicit disclosure. These findings suggest a broader trend in which privacy policies increasingly emphasize legal rights and visible consent mechanisms, while de-emphasizing backend technical safeguards. The results point to a split in compliance communication, possibly influenced by regulatory clarity, enforcement pressure, and shifts in organizational privacy strategy. This study underscores the importance of continued policy auditing and the need for complementary methods that bridge the gap between stated policy and implemented practice in the context of evolving digital governance frameworks.

Extensive efforts in automated approaches for content moderation have been focused on developing models to identify toxic, offensive, and hateful content with the aim of lightening the load for moderators.Yet, it remains uncertain whether improvements on those tasks have truly addressed moderators' needs in accomplishing their work.In this paper, we surface gaps between past research efforts that have aimed to provide automation for aspects of content moderation and the needs of volunteer content moderators, regarding identifying violations of various moderation rules.To do so, we conduct a model review on Hugging Face to reveal the availability of models to cover various moderation rules and guidelines from three exemplar forums.We further put state-of-the-art LLMs to the test, evaluating how well these models perform in flagging violations of platform rules from one particular forum.Finally, we conduct a user survey study with volunteer moderators to gain insight into their perspectives on useful moderation models.Overall, we observe a nontrivial gap, as missing developed models and LLMs exhibit moderate to low performance on a significant portion of the rules.Moderators' reports provide guides for future work on developing moderation assistant models.

Yang Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, Linda Zou. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Abstract Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systematic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and investigate where in the machine learning pipeline such biases can enter a coreference resolution system. We inspect many existing data sets for trans-exclusionary biases, and develop two new data sets for interrogating bias in both crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we will build systems that fail for: quality of service, stereotyping, and over- or under-representation, especially for binary and non-binary trans users.

Correctly resolving textual mentions of people fundamentally entails making inferences about those people.Such inferences raise the risk of systemic biases in coreference resolution systems, including biases that can harm binary and non-binary trans and cis stakeholders.To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and develop two new datasets for interrogating bias in crowd annotations and in existing coreference resolution systems.Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we build systems that lead to many potential harms.