Saurav Ghosh

Saurav Ghosh, Gabriella Polach, Abdou Sow

Large language models (LLMs) are widely used for open-ended tasks, but underspecified prompts can lead to low-quality answers and additional interaction. This paper studies whether structured prompt design improves response quality while reducing user effort. We compare three prompt conditions: a raw prompt, a checklist-improved prompt, and a clarifying-question prompt. We evaluate these conditions across four task types--summarization, planning, explanation, and coding--using three LLM systems: ChatGPT, Claude, and Grok. Each output is scored with a unified rubric covering task completion, correctness, compliance, and clarity. Checklist-improved prompts achieved the highest mean rubric score, 7.50 out of 8, compared with 5.67 for raw prompts and 6.67 for clarifying-question prompts. Checklist prompts also produced the best quality-effort tradeoff, using fewer average tokens than both raw and clarifying prompts. These results suggest that a simple prompt checklist can improve LLM responses while reducing unnecessary interaction.

Saurav Ghosh, Abdou Sow, Luke Zhang

Humanoid robots are difficult to deploy safely because they have high-dimensional bodies, many collision constraints, and must operate near people and obstacles. Safety filters help by modifying a nominal control action when it may violate collision-avoidance constraints. Still, nominal benchmark scores do not fully show how these filters behave in harder environments. In this work, we study the robustness of SPARK humanoid safety filters through replication and stress testing. We replicate the SPARK benchmark case G1SportMode_D1_WG_SO_v1 in MuJoCo and evaluate RSSA, RSSS, SSA, CBF, PFM, and SMA under controlled random seeds. We also built a post-processing pipeline that converts raw SPARK logs into goal-tracking, minimum-distance, and collision-step metrics. Our results show that some methods track the goal more closely, while others reduce collision steps more effectively. The stress tests further indicate that safety behavior can change under obstacle crowding, noisy distance estimates, and delayed obstacle information. These findings suggest that humanoid autonomy should be evaluated beyond nominal performance, using metrics that expose failure modes before deployment.

Saurav Ghosh, Philippe Loustaunau

Rhetorical Frames in AI can be thought of as expressions that describe AI development as a competition between two or more actors, such as governments or companies. Examples of such Frames include robotic arms race, AI rivalry, technological supremacy, cyberwarfare dominance and 5G race. Detection of Rhetorical Frames from open sources can help us track the attitudes of governments or companies towards AI, specifically whether attitudes are becoming more cooperative or competitive over time. Given the rapidly increasing volumes of open sources (online news media, twitter, blogs), it is difficult for subject matter experts to identify Rhetorical Frames in (near) real-time. Moreover, these sources are in general unstructured (noisy) and therefore, detecting Frames from these sources will require state-of-the-art text classification techniques. In this paper, we develop RheFrameDetect, a text classification system for (near) real-time capture of Rhetorical Frames from open sources. Given an input document, RheFrameDetect employs text classification techniques at multiple levels (document level and paragraph level) to identify all occurrences of Frames used in the discussion of AI. We performed extensive evaluation of the text classification techniques used in RheFrameDetect against human annotated Frames from multiple news sources. To further demonstrate the effectiveness of RheFrameDetect, we show multiple case studies depicting the Frames identified by RheFrameDetect compared against human annotated Frames.

Saurav Ghosh, Prithwish Chakraborty, Bryan L. Lewis et al.

Real-time monitoring and responses to emerging public health threats rely on the availability of timely surveillance data. During the early stages of an epidemic, the ready availability of line lists with detailed tabular information about laboratory-confirmed cases can assist epidemiologists in making reliable inferences and forecasts. Such inferences are crucial to understand the epidemiology of a specific disease early enough to stop or control the outbreak. However, construction of such line lists requires considerable human supervision and therefore, difficult to generate in real-time. In this paper, we motivate Guided Deep List, the first tool for building automated line lists (in near real-time) from open source reports of emerging disease outbreaks. Specifically, we focus on deriving epidemiological characteristics of an emerging disease and the affected population from reports of illness. Guided Deep List uses distributed vector representations (ala word2vec) to discover a set of indicators for each line list feature. This discovery of indicators is followed by the use of dependency parsing based techniques for final extraction in tabular form. We evaluate the performance of Guided Deep List against a human annotated line list provided by HealthMap corresponding to MERS outbreaks in Saudi Arabia. We demonstrate that Guided Deep List extracts line list features with increased accuracy compared to a baseline method. We further show how these automatically extracted line list features can be used for making epidemiological inferences, such as inferring demographics and symptoms-to-hospitalization period of affected individuals.

Saurav Ghosh, Prithwish Chakraborty, Elaine O. Nsoesie et al.

In retrospective assessments, internet news reports have been shown to capture early reports of unknown infectious disease transmission prior to official laboratory confirmation. In general, media interest and reporting peaks and wanes during the course of an outbreak. In this study, we quantify the extent to which media interest during infectious disease outbreaks is indicative of trends of reported incidence. We introduce an approach that uses supervised temporal topic models to transform large corpora of news articles into temporal topic trends. The key advantages of this approach include, applicability to a wide range of diseases, and ability to capture disease dynamics - including seasonality, abrupt peaks and troughs. We evaluated the method using data from multiple infectious disease outbreaks reported in the United States of America (U.S.), China and India. We noted that temporal topic trends extracted from disease-related news reports successfully captured the dynamics of multiple outbreaks such as whooping cough in U.S. (2012), dengue outbreaks in India (2013) and China (2014). Our observations also suggest that efficient modeling of temporal topic trends using time-series regression techniques can estimate disease case counts with increased precision before official reports by health organizations.

Saurav Ghosh, Prithwish Chakraborty, Emily Cohn et al.

Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper, we motivate a disease vocabulary driven word2vec model (Dis2Vec) to model diseases and constituent attributes as word embeddings from the HealthMap news corpus. We use these word embeddings to automatically create disease taxonomies and evaluate our model against corresponding human annotated taxonomies. We compare our model accuracies against several state-of-the art word2vec methods. Our results demonstrate that Dis2Vec outperforms traditional distributed vector representations in its ability to faithfully capture taxonomical attributes across different class of diseases such as endemic, emerging and rare.