Search

Scholarly Works (4 results)

Sort By:

Thesis
Peer Reviewed

One Step towards Autonomous AI Agent: Reasoning, Alignment and Planning

Chen, Xiusi
Advisor(s): Wang, Wei

UCLA Electronic Theses and Dissertations (2024)

The recent development of artificial intelligence (AI) has facilitated the prosperity of foundation models, such as large language models (LLMs) and vision models. The foundation models have reshaped the way people interact with tools to improve productivity and creativity by taking over many use cases where people use conventional computer software. Being aware of the promising emerging abilities observed from the foundation models, a more interactive picture has been envisioned where the foundation models drive a group of AI agents that play different roles to fulfill more diverse and complex tasks, further benefiting human society. Like humans, AI agents should be able to reason and plan over complex tasks, and they should also be well aligned with human preferences and values. Advanced foundation models provide a solid foundation for the implementation of AI agents. However, agents based on the current foundation models have intrinsic limitations inherited from existing foundation models. In addition to hallucination, these foundation models can demonstrate biases presented in their training data, resulting in output that can be discriminatory. LLMs can expose sensitive or personal information embedded in their training data, risking user privacy and security. Finally, due to the generative nature of the prevailing foundation models, it is desirable to incorporate planning modules generatively, so the planning process can be seamlessly accomplished during the generation process. In summary, the gaps between the current state-of-the-art and the goals underscore the need for further efforts to improve the reasoning ability, the alignment of human values and the generative planning ability of the foundation models.

My ultimate research goal is to build AI agents that are reliable, unbiased, and capable of planning so that they can be safely and effectively applied in various domains. To achieve this goal, I have divided my research into the following subtasks:

1. Knowledge-Enhanced Reasoning that aims to improve the factual accuracy and logical coherence of LLM outputs by integrating external knowledge.2. Minimally Supervised Data Generation and Selection that aims to improve the efficiency of fine-tuning or in-context learning by selecting the most informative training data. 3. Automatic Constitution Discovery and Self-alignment that aims to mitigate the risk of generating incorrect, nonsensical, biased or private information. 4. Agents Planning that aims to enable multi-agent strategic learning by incorporating generative goal-guided planning.

In this thesis, I will first emphasize the significance of building such reliable, unbiased, capable-of-planning AI agents, and then introduce four lines of my work, and finally the future challenges and opportunities.

Cover page: One Step towards Autonomous AI Agent: Reasoning, Alignment and Planning

Article
Peer Reviewed

COVID-19 Surveiller: toward a robust and effective pandemic surveillance system based on social media mining

UCLA Previously Published Works (2022)

The outbreak of the novel coronavirus, COVID-19, has become one of the most severe pandemics in human history. In this paper, we propose to leverage social media users as social sensors to simultaneously predict the pandemic trends and suggest potential risk factors for public health experts to understand spread situations and recommend proper interventions. More precisely, we develop novel deep learning models to recognize important entities and their relations over time, thereby establishing dynamic heterogeneous graphs to describe the observations of social media users. A dynamic graph neural network model can then forecast the trends (e.g. newly diagnosed cases and death rates) and identify high-risk events from social media. Based on the proposed computational method, we also develop a web-based system for domain experts without any computer science background to easily interact with. We conduct extensive experiments on large-scale datasets of COVID-19 related tweets provided by Twitter, which show that our method can precisely predict the new cases and death rates. We also demonstrate the robustness of our web-based pandemic surveillance system and its ability to retrieve essential knowledge and derive accurate predictions across a variety of circumstances. Our system is also available at http://scaiweb.cs.ucla.edu/covidsurveiller/. This article is part of the theme issue 'Data science approachs to infectious disease surveillance'.

Cover page: COVID-19 Surveiller: toward a robust and effective pandemic surveillance system based on social media mining

Article

How the Experience of California Wildfires Shapes Twitter Climate Change Framings

UC Irvine Previously Published Works (2023)

Abstract: Climate communication scientists search for effective message strategies to engage the ambivalent public in support of climate advocacy. The personal experience of wildfire is expected to render climate change impacts more concretely, pointing to a potential message strategy to engage the public. This study examined Twitter discourse related to climate change during the onset of 20 wildfires in California between years 2017-2021. We content analyzed tweets geographically and temporally proximal to the occurrence of wildfires to discover framings and examined how mean frequencies in climate framings changed before and after fires. Results identified three predominant climate framings: making explicit links between wildfire and climate change, suggesting climate actions, and attributing climate change to adversities besides wildfires. Mean tweet frequencies linking wildfire with climate change and attributing adversities increased significantly after the onset of fire while urging climate action tweets did not. Temporal analysis of tweet frequencies of tweets linking wildfires to climate change showed that discussion increased after the onset of a fire but persisted typically no more than one to two weeks. External real-world events happening simultaneously during wildfires also triggered climate discussions. Our findings contribute to identifying how the personal experience of wildfire shapes Twitter discussion related to climate change, and how these narratives change over time before and after wildfires, leading to insights into critical time points after wildfire for implementing message strategies to increase public engagement on climate change impacts and policy.

Cover page: How the Experience of California Wildfires Shapes Twitter Climate Change Framings

Creative Commons 'BY' version 4.0 license

Article
Peer Reviewed

How the experience of California wildfires shape Twitter climate change framings

UC Irvine Previously Published Works (2024)

Climate communication scientists search for effective message strategies to engage the ambivalent public in support of climate advocacy. The personal experience of wildfire is expected to render climate change impacts more concretely, pointing to a potential message strategy to engage the public. This study examined Twitter discourse related to climate change during the onset of 20 wildfires in California between the years 2017 and 2021. In this mixed method study, we analyzed tweets geographically and temporally proximal to the occurrence of wildfires to discover framings and examined how frequencies in climate framings changed before and after fires. Results identified three predominant climate framings: linking wildfire to climate change, suggesting climate actions, and attributing climate change to adversities besides wildfires. Mean tweet frequencies linking wildfire to climate change and attributing adversities increased significantly after the onset of fire. While suggesting climate action tweets also increased, the increase was not statistically significant. Temporal analysis of tweet frequencies for the three themes of tweets showed that discussion increased after the onset of a fire but persisted typically no more than 2 weeks. For fires that burned for longer periods of more than a month, external events triggered climate discussions. Our findings contribute to identifying how the personal experience of wildfire shapes Twitter discussion related to climate change, and how these framings change over time during wildfire events, leading to insights into critical time points after wildfire for implementing message strategies to increase public engagement on climate change impacts and policy.