Search Results for author:
Found 33 papers, 12 papers with code
Generative Semantic Communication: Architectures, Technologies, and Applications
This system features two LLM-based AI agents at both the transmitter and receiver, serving as "brains" to enable powerful information understanding and content regeneration capabilities, respectively.
Cross-Domain Recommendation Meets Large Language Models
Cross-domain recommendation (CDR) has emerged as a promising solution to the cold-start problem, faced by single-domain recommender systems.
ORIS: Online Active Learning Using Reinforcement Learning-based Inclusive Sampling for Robust Streaming Analytics System
ORIS aims to create a novel Deep Q-Network-based strategy to sample incoming documents that minimize human errors in labeling and enhance the ML model performance.
Towards Robust Text Classification: Mitigating Spurious Correlations with Causal Learning
In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels.
Advancing Interpretability in Text Classification through Prototype Learning
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical.
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability.
Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge
We also compared the performance of GPT 3. 5 and GPT 4 models using different prompts: na\"ive, layperson-definition, role-playing, and professional-definition.
Neural Symbolic Logical Rule Learner for Interpretable Learning
Rule-based neural networks stand out for enabling interpretable classification by learning logical rules for both prediction and interpretation.
Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models
We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9, 935 images of 67 countries and 10 concept classes; (2) the underlying implicit and potentially stereotypical cultural associations with a cultural artifact extraction task; and (3) an approach to adapt cultural representation in an image based on extracted associations using a modular pipeline, CultureAdapt.
Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis
We propose a unique debiasing technique, Social Contact Debiasing (SCD), that instruction-tunes these models with unbiased responses to prompts.
BiasDora: Exploring Hidden Biased Associations in Vision-Language Models
Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime.
Countering Mainstream Bias via End-to-End Adaptive Local Learning
In this paper, we identify two root causes of this mainstream bias: (i) discrepancy modeling, whereby CF algorithms focus on modeling mainstream users while neglecting niche users with unique preferences; and (ii) unsynchronized learning, where niche users require more training epochs than mainstream users to reach peak performance.
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
Exploring the full spectrum of trade-offs between privacy, model utility, and runtime efficiency is critical for practical unlearning scenarios.
Global Voices, Local Biases: Socio-Cultural Prejudices across Languages
Finally, we highlight the significance of these social biases and the new dimensions through an extensive comparison of embedding methods, reinforcing the need to address them in pursuit of more equitable language models.
Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model
Question generation is a widely used data augmentation approach with extensive applications, and extracting qualified candidate answers from context passages is a critical step for most question generation systems.
Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning
Pre-trained Language Models are widely used in many important real-world applications.
A meta learning scheme for fast accent domain expansion in Mandarin speech recognition
We combine the methods of meta learning and freeze of model parameters, which makes the recognition performance more stable in different cases and the training faster about 20%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts
A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a user's goals and needs.
Enhancing User Personalization in Conversational Recommenders
Conversational recommenders are emerging as a powerful tool to personalize a user's recommendation experience.
Evolution of Filter Bubbles and Polarization in News Recommendation
However, most existing work focuses on a static setting or over a short-time window, leaving open questions about the long-term and dynamic impacts of news recommendations.
Understanding Best Subset Selection: A Tale of Two C(omplex)ities
Furthermore, we show that a margin condition depending on similar margin quantity and complexity measures is also necessary for model consistency of BSS.
Towards Fair Conversational Recommender Systems
Conversational recommender systems have demonstrated great success.
Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems
Conversational recommender systems (CRS) have shown great success in accurately capturing a user's current and detailed preference through the multi-round interaction cycle while effectively guiding users to a more personalized recommendation.
Evolution of Popularity Bias: Empirical Study and Debiasing
and how to debias in this long-term dynamic process?
Supervised Homogeneity Fusion: a Combinatorial Approach
Fusing regression coefficients into homogenous groups can unveil those coefficients that share a common value within each group.
Session-based Recommendation with Hypergraph Attention Networks
Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms.
End-to-end Learning for Fair Ranking Systems
The end-to-end SPOFR framework includes a constrained optimization sub-model and produces ranking policies that are guaranteed to satisfy fairness constraints while allowing for fine control of the fairness-utility tradeoff.
Fairness-aware Personalized Ranking Recommendation via Adversarial Learning
This is paper is an extended and reorganized version of our SIGIR 2020~\cite{zhu2020measuring} paper.
Popularity-Opportunity Bias in Collaborative Filtering
This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias.
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition
Knowledge of a disease includes information of various aspects of the disease, such as signs and symptoms, diagnosis and treatment.
Learning Markov models via low-rank optimization
We show that one can estimate the full transition model accurately using a trajectory of length that is proportional to the total number of states.
Fairness-Aware Recommendation of Information Curators
This paper highlights our ongoing efforts to create effective information curator recommendation models that can be personalized for individual users, while maintaining important fairness properties.
Robust high dimensional factor models with applications to statistical machine learning
Factor models are a class of powerful statistical models that have been widely used to deal with dependent measurements that arise frequently from various applications from genomics and neuroscience to economics and finance.
