arXiv subjects

Ran Hu

Publications and source records attributed to Ran Hu.

6 recordsLinked to original sources

arXiv2025

FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace

The emergence of agentic AI, powered by Large Language Models (LLMs), marks a paradigm shift from reactive generative systems to proactive, goal-oriented autonomous agents capable of sophisticated planning, memory, and tool use. This evolution presents a novel opportunity to address long-standing challenges in complex digital environments. Core tasks on Consumer-to-Consumer (C2C) e-commerce platforms often require users to navigate complex Graphical User Interfaces (GUIs), making the experience time-consuming for both buyers and sellers. This paper introduces a novel approach to simplify these interactions through an LLM-powered agentic assistant. This agent functions as a new, conversational entry point to the marketplace, shifting the primary interaction model from a complex GUI to an intuitive AI agent. By interpreting natural language commands, the agent automates key high-friction workflows. For sellers, this includes simplified updating and renewal of listings, and the ability to send bulk messages. For buyers, the agent facilitates a more efficient product discovery process through conversational search. We present the architecture for Facebook Marketplace Assistant (FaMA), arguing that this agentic, conversational paradigm provides a lightweight and more accessible alternative to traditional app interfaces, allowing users to manage their marketplace activities with greater efficiency. Experiments show FaMA achieves a 98% task success rate on solving complex tasks on the marketplace and enables up to a 2x speedup on interaction time.

cs.AI↗

arXiv2025

Streamlining Biomedical Research with Specialized LLMs

In this paper, we propose a novel system that integrates state-of-the-art, domain-specific large language models with advanced information retrieval techniques to deliver comprehensive and context-aware responses. Our approach facilitates seamless interaction among diverse components, enabling cross-validation of outputs to produce accurate, high-quality responses enriched with relevant data, images, tables, and other modalities. We demonstrate the system's capability to enhance response precision by leveraging a robust question-answering model, significantly improving the quality of dialogue generation. The system provides an accessible platform for real-time, high-fidelity interactions, allowing users to benefit from efficient human-computer interaction, precise retrieval, and simultaneous access to a wide range of literature and data. This dramatically improves the research efficiency of professionals in the biomedical and pharmaceutical domains and facilitates faster, more informed decision-making throughout the R\&D process. Furthermore, the system proposed in this paper is available at https://synapse-chat.patsnap.com.

cs.CL↗

arXiv2024

Computing the Center of Uncertain Points on Cactus Graphs

In this paper, we consider the (weighted) one-center problem of uncertain points on a cactus graph. Given are a cactus graph $G$ and a set of $n$ uncertain points. Each uncertain point has $m$ possible locations on $G$ with probabilities and a non-negative weight. The (weighted) one-center problem aims to compute a point (the center) $x^*$ on $G$ to minimize the maximum (weighted) expected distance from $x^*$ to all uncertain points. No previous algorithm is known for this problem. In this paper, we propose an $O(|G| + mn\log mn)$-time algorithm for solving it. Since the input is $O(|G|+mn)$, our algorithm is almost optimal.

cs.DS↗

arXiv2024

On the Approximability of the Yolk in the Spatial Model of Voting

In the spatial model of voting, the yolk and LP (linear programming) yolk are important solution concepts for predicting outcomes for a committee of voters. McKelvey and Tovey showed that the LP yolk provides a lower bound approximation for the size of the yolk and there has been considerable debate on whether the LP yolk is a good approximation of the yolk. In this paper, we show that for an odd number of voters in a two-dimensional space that the yolk radius is at most twice the size of the LP yolk radius. However, we also show that (1) even in this setting, the LP yolk center can be arbitrarily far away from the yolk center (relative to the radius of the yolk) and (2) for all other settings (an even number of voters or in dimension $k\geq 3$) that the LP yolk can be arbitrarily small relative to the yolk. Thus, in general, the LP yolk can be an arbitrarily poor approximation of the yolk.

cs.GT↗

arXiv2024

PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry

Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering. However, the application of LLMs in specialized domains like biopharmaceuticals and chemistry remains largely unexplored. These fields are characterized by intricate terminologies, specialized knowledge, and a high demand for precision areas where general purpose LLMs often fall short. In this study, we introduce PharmaGPT, a suite of domain specilized LLMs with 13 billion and 70 billion parameters, specifically trained on a comprehensive corpus tailored to the Bio-Pharmaceutical and Chemical domains. Our evaluation shows that PharmaGPT surpasses existing general models on specific-domain benchmarks such as NAPLEX, demonstrating its exceptional capability in domain-specific tasks. Remarkably, this performance is achieved with a model that has only a fraction, sometimes just one-tenth-of the parameters of general-purpose large models. This advancement establishes a new benchmark for LLMs in the bio-pharmaceutical and chemical fields, addressing the existing gap in specialized language modeling. It also suggests a promising path for enhanced research and development, paving the way for more precise and effective NLP applications in these areas.

cs.CL↗

arXiv2020

Twitter discussions and emotions about COVID-19 pandemic: a machine learning approach

The objective of the study is to examine coronavirus disease (COVID-19) related discussions, concerns, and sentiments that emerged from tweets posted by Twitter users. We analyze 4 million Twitter messages related to the COVID-19 pandemic using a list of 25 hashtags such as "coronavirus," "COVID-19," "quarantine" from March 1 to April 21 in 2020. We use a machine learning approach, Latent Dirichlet Allocation (LDA), to identify popular unigram, bigrams, salient topics and themes, and sentiments in the collected Tweets. Popular unigrams include "virus," "lockdown," and "quarantine." Popular bigrams include "COVID-19," "stay home," "corona virus," "social distancing," and "new cases." We identify 13 discussion topics and categorize them into five different themes, such as "public health measures to slow the spread of COVID-19," "social stigma associated with COVID-19," "coronavirus news cases and deaths," "COVID-19 in the United States," and "coronavirus cases in the rest of the world". Across all identified topics, the dominant sentiments for the spread of coronavirus are anticipation that measures that can be taken, followed by a mixed feeling of trust, anger, and fear for different topics. The public reveals a significant feeling of fear when they discuss the coronavirus new cases and deaths than other topics. The study shows that Twitter data and machine learning approaches can be leveraged for infodemiology study by studying the evolving public discussions and sentiments during the COVID-19. Real-time monitoring and assessment of the Twitter discussion and concerns can be promising for public health emergency responses and planning. Already emerged pandemic fear, stigma, and mental health concerns may continue to influence public trust when there occurs a second wave of COVID-19 or a new surge of the imminent pandemic.

cs.SI↗