Search for: All records

The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design and retrieval augmented generation for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA. 

Data visualization has become an increasingly important means of effective data communication and has played a vital role in broadcasting the progression of COVID-19. Accessible data representations, however, have lagged behind, leaving areas of information out of reach for many blind and visually impaired (BVI) users. In this work, we sought to understand (1) the accessibility of current implementations of visualizations on the web; (2) BVI users’ preferences and current experiences when accessing data-driven media; (3) how accessible data representations on the web address these users’ access needs and help them navigate, interpret, and gain insights from the data; and (4) the practical challenges that limit BVI users’ access and use of data representations. To answer these questions, we conducted a mixed-methods study consisting of an accessibility audit of 87 data visualizations on the web to identify accessibility issues, an online survey of 127 screen reader users to understand lived experiences and preferences, and a remote contextual inquiry with 12 of the survey respondents to observe how they navigate, interpret, and gain insights from accessible data representations. Our observations during this critical period of time provide an understanding of the widespread accessibility issues encountered across online data visualizations, the impact that data accessibility inequities have on the BVI community, the ways screen reader users sought access to data-driven information and made use of online visualizations to form insights, and the pressing need to make larger strides towards improving data literacy, building confidence, and enriching methods of access. Based on our findings, we provide recommendations for researchers and practitioners to broaden data accessibility on the web. 

Online data visualizations play an important role in informing public opinion but are often inaccessible to screen reader users. To address the need for accessible data representations on the web that provide direct, multimodal, and up-to-date access to the data, we investigate audio data narratives –which combine textual descriptions and sonification (the mapping of data to non-speech sounds). We conduct two co-design workshops with screen reader users to define design principles that guide the structure, content, and duration of a data narrative. Based on these principles and relevant auditory processing characteristics, we propose a dynamic programming approach to automatically generate an audio data narrative from a given dataset. We evaluate our approach with 16 screen reader users. Findings show with audio narratives, users gain significantly more insights from the data. Users describe data narratives help them better extract and comprehend the information in both the sonification and description. 

Data visualization has become an increasingly important means of effective data communication and has played a vital role in broadcasting the progression of COVID-19. Accessible data representations, on the other hand, have lagged behind, leaving areas of information out of reach for many blind and visually impaired (BVI) users. In this work, we sought to understand (1) the accessibility of current implementations of visualizations on the web; (2) BVI users’ preferences and current experiences when accessing data-driven media; (3) how accessible data representations on the web address these users’ access needs and help them navigate, interpret, and gain insights from the data; and (4) the practical challenges that limit BVI users’ access and use of data representations. To answer these questions, we conducted a mixed-methods study consisting of an accessibility audit of 87 data visualizations on the web to identify accessibility issues, an online survey of 127 screen reader users to understand lived experiences and preferences, and a remote contextual inquiry with 12 of the survey respondents to observe how they navigate, interpret and gain insights from accessible data representations. Our observations during this critical period of time provide an understanding of the widespread accessibility issues encountered across online data visualizations, the impact that data accessibility inequities have on the BVI community, the ways screen reader users sought access to data-driven information and made use of online visualizations to form insights, and the pressing need to make larger strides towards improving data literacy, building confidence, and enriching methods of access. Based on our findings, we provide recommendations for researchers and practitioners to broaden data accessibility on the web. 

We increasingly rely on up-to-date, data-driven graphs to understand our environments and make informed decisions. However, many of the methods blind and visually impaired users (BVI) rely on to access data-driven information do not convey important shape-characteristics of graphs, are not refreshable, or are prohibitively expensive. To address these limitations, we introduce two refreshable, 1-DOF audio-haptic interfaces based on haptic cues fundamental to object shape perception. Slide-tone uses finger position with sonification, and Tilt-tone uses fingerpad contact inclination with sonification to provide shape feedback to users. Through formative design workshops (n = 3) and controlled evaluations (n = 8), we found that BVI participants appreciated the additional shape information, versatility, and reinforced understanding these interfaces provide; and that task accuracy was comparable to using interactive tactile graphics or sonification alone. Our research offers insight into the benefits, limitations, and considerations for adopting these haptic cues into a data visualization context.