Search Results for author:
Found 24 papers, 9 papers with code
Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks.
Algorithmic Collective Action with Two Collectives
We find that the unintentional interactions between collectives can be quite significant; a collective acting in isolation may be able to achieve their objective (e. g., improve classification outcomes for themselves or promote a particular item), but when a second collective acts simultaneously, the efficacy of the first group drops by as much as $75\%$.
AMUN: Adversarial Machine UNlearning
Adversarial examples naturally belong to the distribution imposed by the model on the input space; fine-tuning the model on the adversarial examples closest to the corresponding forget samples (a) localizes the changes to the decision boundary of the model around each forget sample and (b) avoids drastic changes to the global behavior of the model, thereby preserving the model's accuracy on test samples.
A Zero-Shot Generalization Framework for LLM-Driven Cross-Domain Sequential Recommendation
By mitigating domain bias and enhancing the transferability of sequential patterns, our method provides a scalable and robust approach for achieving more effective zero-shot recommendations across domains.
Venire: A Machine Learning-Guided Panel Review System for Community Content Moderation
The problem is not the root disagreements themselves.
LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
We show that although a lower Lipschitz constant increases the robustness of a single model, it is not as beneficial in training robust ensembles as it increases the transferability rate of adversarial examples across models in the ensemble.
Spectrum Extraction and Clipping for Implicitly Linear Layers
We show the effectiveness of automatic differentiation in efficiently and correctly computing and controlling the spectrum of implicitly linear operators, a rich family of layer types including all standard convolutional and dense layers.
CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations
As large-scale language models become the standard for text generation, there is a greater need to tailor the generations to be more or less concise, targeted, and informative, depending on the audience/application.
A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer
In addition, with a simple post-hoc interpolation, PrepRec can improve the performance of existing sequential recommenders on average by 13. 8\% in Recall@10 and 29. 5% in NDCG@10.
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Finally, we systematically evaluate and analyze eight mainstream LLMs and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks.
Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems
Thus, we use the statistical characteristics of the user-item interaction matrix to identify dataset-independent representations for users and items.
Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation
When answering complex questions, large language models (LLMs) may produce answers that do not satisfy all criteria of the question.
Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
Furthermore, we identify an issue of imbalanced utilization of the outline information in the precise outline-conditioned generation, which is ubiquitously observed across fine-tuned models and zero-shot inference models.
Inform the uninformed: Improving Online Informed Consent Reading with an AI-Powered Chatbot
By comparing the chatbot with form-based interaction, we found the chatbot improved consent form reading, promoted participants' feelings of agency, and closed the power gap between the participant and the researcher.
Audience-Centric Natural Language Generation via Style Infusion
While existing approaches demonstrate textual style transfer with large volumes of parallel or non-parallel data, we argue that grounding style on audience-independent external factors is innately limiting for two reasons.
What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys
We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge in the context of conversational surveys.
Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework
We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs.
GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation
We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together.
Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems.
Discovering Strategic Behaviors for Collaborative Content-Production in Social Networks
Different strategies give rise to different social payoffs, the best performing individuals exhibit stability in their preference over the discovered strategies, which indicates the emergence of strategic behavior, and the stability of strategy preference is correlated with high payoffs.
Social and Information Networks Physics and Society
An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms
We develop a novel induced relational graph convolutional network (IR-GCN) framework to address the question.
Mining Hidden Populations through Attributed Search
When the property of the target entities is not directly queryable via the API, we refer to the property as `hidden' and the population as a hidden population.
Growing Attributed Networks through Local Processes
Despite the knowledge that individuals use limited resources to form connections to similar others, we lack an understanding of how local and resource-constrained mechanisms explain the emergence of rich structural properties found in real-world networks.
Social and Information Networks
Improving Latent User Models in Online Social Media
Modern social platforms are characterized by the presence of rich user-behavior data associated with the publication, sharing and consumption of textual content.
