Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
An exploratory study of reactions to bot comments on GitHub
The widespread use of bots to support software development makes social coding platforms such as GitHub a particularly rich source of data for the study of human-bot interaction. Software development bots are used to automate repetitive tasks, interacting with their human counterparts via comments posted on the various discussion interfaces available on such platforms. One type of interaction supported by GitHub involves reacting to comments using predefined emoji. To investigate how users react to bot comments, we conducted an observational study comprising 54 million GitHub comments, with a particular focus on comments that elicited the laugh reaction. The results from our analysis suggest that some reaction types are not equally distributed across human and bot comments and that a bot’s design and purpose influence the types of reactions it receives. Furthermore, while the laugh reaction is not exclusively used to express laughter, it can be used to convey humor when a bot behaves unexpectedly. These insights could inform the way bots are designed and help developers equip them with the ability to recognize and recover from unanticipated situations. In turn, bots could better support the communication, collaboration, and productivity of teams using social coding platforms.
Action and trajectory planning for urban autonomous driving with hierarchical reinforcement learning
Reinforcement Learning (RL) has made promising progress in planning and decision-making for Autonomous Vehicles (AVs) in simple driving scenarios. However, existing RL algorithms for AVs fail to learn critical driving skills in complex urban scenarios. First, urban driving scenarios require AVs to handle multiple driving tasks of which conventional RL algorithms are incapable. Second, the presence of other vehicles in urban scenarios results in a dynamically changing environment, which challenges RL algorithms to plan the action and trajectory of the AV. In this work, we propose an action and trajectory planner using Hierarchical Reinforcement Learning (atHRL) method, which models the agent behavior in a hierarchical model by using the mid-level perception of the lidar and birdeye view. The proposed atHRL method learns to make decisions about the agent’s future trajectory and computes target waypoints under continuous settings based on a hierarchical DDPG algorithm. The waypoints planned by the atHRL model are then sent to a low-level controller to generate the steering and throttle commands required for the vehicle maneuver. We empirically verify the efficacy of atHRL through extensive experiments in complex urban driving scenarios that compose multiple tasks with the presence of other vehicles in the CARLA simulator. The experimental results suggest a significant performance improvement compared to the state-of-the-art RL methods.
TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.
Global-to-Local Support Spectrums for Language Model Explainability
Existing sample-based methods, like influence functions and representer points, measure the importance of a training point by approximating the effect of its removal from training. As such, they are skewed towards outliers and points that are very close to the decision boundaries. The explanations provided by these methods are often static and not specific enough for different test points. In this paper, we propose a method to generate an explanation in the form of support spectrums which are based on two main ideas: the support sets and a global-to-local importance measure. The support set is the set of training points, in the predicted class, that ``lie in between’’ the test point and training points in the other classes. They indicate how well the test point can be distinguished from the points not in the predicted class. The global-to-local importance measure is obtained by decoupling existing methods into the global and local components which are then used to select the points in the support set. Using this method, we are able to generate explanations that are tailored to specific test points. In the experiments, we show the effectiveness of the method in image classification and text generation tasks.
Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms
Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information or model fine-tuning, have become less suitable for LLMs, especially closed-source commercial APIs. This leads to a growing need to explore the untapped area of black-box approaches for LLM uncertainty estimation. To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency. We then benchmark these methods on two key tasks-confidence calibration and failure prediction-across five types of datasets (e.g., commonsense and arithmetic reasoning) and five widely-used LLMs including GPT-4 and LLaMA 2 Chat. Our analysis uncovers several key insights: 1) LLMs, when verbalizing their confidence, tend to be overconfident, potentially imitating human patterns of expressing confidence. 2) As model capability scales up, both calibration and failure prediction performance improve. 3) Employing our proposed strategies, such as human-inspired prompts, consistency among multiple responses, and better aggregation strategies can help mitigate this overconfidence from various perspectives. 4) Comparisons with white-box methods indicate that while white-box methods perform better, the gap is narrow, e.g., 0.522 to 0.605 in AUROC. Despite these advancements, none of these techniques consistently outperform others, and all investigated methods struggle in challenging tasks, such as those requiring professional knowledge, indicating significant scope for improvement. We believe this study can serve as a strong baseline and provide insights for eliciting confidence in black-box LLMs.
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data
The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text by an LLM. In this paper, we show that this problem can be tackled by watermarking, i.e., by enabling an LLM to generate synthetic texts with embedded watermarks that contain information about their source(s). We identify the key properties of such watermarking frameworks (e.g., source attribution accuracy, robustness against adversaries), and propose a source attribution framework that satisfies these key properties due to our algorithmic designs. Our framework enables an LLM to learn an accurate mapping from the generated texts to data providers, which sets the foundation for effective source attribution. Extensive empirical evaluations show that our framework achieves effective source attribution.
Batch and Sequential Unlearning for Neural Networks
With the increasing deployment of machine learning models trained on personal data, machine unlearning has become crucial for data owners to exercise their “right to be forgotten” and protect their privacy. While model owners can retrain the models without the erased data to achieve this goal, this process is often prohibitively expensive. Previous works have shown that Newton’s method can be applied to linear models to unlearn multiple data points in batch (batch unlearning) with minimal iterations. However, adapting this method to non-linear models, such as neural networks, poses significant challenges due to the presence of degenerate Hessians. This problem becomes more pronounced when unlearning is performed sequentially (sequential unlearning). Existing techniques that tried to tackle this degeneracy often 1) incur unlearning updates with excessively large norm that yield unsatisfactory unlearning performance and 2) may require manual tuning of regularization hyperparameters. In this work, we propose new unlearning algorithms that leverage cubic regularization for Newton’s method to address both challenges. We discuss the theoretical benefits of our method and empirically show that our algorithms can efficiently achieve competitive performance in both batch and sequential unlearning on real-world datasets.
WaterDrum: Watermarking for Data-centric Unlearning Metric
Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. However, existing utility-centric unlearning metrics (based on model utility) may fail to accurately evaluate the extent of unlearning in realistic settings such as when (a) the forget and retain set have semantically similar content, (b) retraining the model from scratch on the retain set is impractical, and/or (c) the model owner can improve the unlearning metric without directly performing unlearning on the LLM. This paper presents the first data-centric unlearning metric for LLMs called WaterDrum that exploits robust text watermarking for overcoming these limitations. We also introduce new benchmark datasets for LLM unlearning that contain varying levels of similar data points and can be used to rigorously evaluate unlearning algorithms using WaterDrum.
talks
Talk 1 on Relevant Topic in Your Field
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
This is a description of a teaching experience. You can use markdown like any other post.