Search Results for author:
Found 39 papers, 9 papers with code
Say It Another Way: A Framework for User-Grounded Paraphrasing
Small changes in how a prompt is worded can lead to meaningful differences in the behavior of large language models (LLMs), raising concerns about the stability and reliability of their evaluations.
Crossing Boundaries: Leveraging Semantic Divergences to Explore Cultural Novelty in Cooking Recipes
By introducing a set of Jensen-Shannon Divergence metrics for novelty, we leverage this dataset to analyze textual divergences when recipes from one community are modified by another with a different cultural background.
The Curious Case of Arbitrariness in Machine Learning
Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions.
Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy
The increased screen time and isolation caused by the COVID-19 pandemic have led to a significant surge in cases of online grooming, which is the use of strategies by predators to lure children into sexual exploitation.
Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML
In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores.
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards outputs that are intended to be both less harmful and more helpful.
Multilingual Hallucination Gaps in Large Language Models
In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps.
FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation
To the best of our knowledge, we are the first to introduce a fairness based finetuning through LoRA.
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown.
On the Implicit Relation Between Low-Rank Adaptation and Differential Privacy
As models grow in size, full fine-tuning all of their parameters becomes increasingly impractical.
Understanding the Local Geometry of Generative Model Manifolds
Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training.
Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild
Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs).
Towards More Realistic Extraction Attacks: An Adversarial Perspective
Language models are prone to memorizing parts of their training data which makes them vulnerable to extraction attacks.
Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
The rise of foundation models holds immense promise for advancing AI, but this progress may amplify existing risks and inequalities, leaving marginalized communities behind.
Differentially Private Clustered Federated Learning
To address this gap, we propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients' clusters correctly.
Understanding Intrinsic Socioeconomic Biases in Large Language Models
Large Language Models (LLMs) are increasingly integrated into critical decision-making processes, such as loan approvals and visa applications, where inherent biases can lead to discriminatory outcomes.
The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity
Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection.
Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendations
In this work, we identify these biases in recommendations for artists from underrepresented cultural groups in prototype-based matrix factorization methods.
Fairness Incentives in Response to Unfair Dynamic Pricing
We find that, upon deploying a learned tax and redistribution policy, social welfare improves on that of the fairness-agnostic baseline, and approaches that of the analytically optimal fairness-aware baseline for the multi-armed and contextual bandit settings, and surpassing it by 13. 19% in the full RL setting.
From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain.
Balancing Act: Constraining Disparate Impact in Sparse Models
Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or storage capacities.
Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness
Despite the essential need for comprehensive considerations in responsible AI, factors like robustness, fairness, and causality are often studied in isolation.
Tidying Up the Conversational Recommender Systems' Biases
The growing popularity of language models has sparked interest in conversational recommender systems (CRS) within both industry and research circles.
Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discovery
As online music platforms grow, music recommender systems play a vital role in helping users navigate and discover content within their vast musical databases.
Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces
In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes.
Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements
The growing utilization of machine learning (ML) in decision-making processes raises questions about its benefits to society.
Privacy-Preserving Fair Item Ranking
Users worldwide access massive amounts of curated data in the form of rankings on a daily basis.
Analyzing the Effect of Sampling in GNNs on Individual Fairness
We evaluate two popular GNN methods: Graph Convolutional Network (GCN), which trains on the entire graph, and GraphSAGE, which uses probabilistic random walks to create subgraphs for mini-batch training, and assess the effects of sub-sampling on individual fairness.
FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks
Empirical evaluation on real-world datasets indicates that FETA is not only able to guarantee fairness on-the-fly at prediction time but also is able to train accurate models exhibiting a much higher degree of individual fairness.
PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning
Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity.
PrivFair: a Library for Privacy-Preserving Fairness Auditing
Machine learning (ML) has become prominent in applications that directly affect people's quality of life, including in healthcare, justice, and finance.
Post-processing Counterexample-guided Fairness Guarantees in Neural Networks
There is an increasing interest in adopting high-capacity machine learning models such as deep neural networks to semi-automate human decisions.
Counterexample-Guided Learning of Monotonic Neural Networks
Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning.
User Profiling Using Hinge-loss Markov Random Fields
In this paper, we propose a mechanism to infer a variety of user characteristics, such as, age, gender and personality traits, which can then be compiled into a user profile.
Compiling Stochastic Constraint Programs to And-Or Decision Diagrams
In this paper we show how identifying and exploiting these identical subproblems can simplify solving them and leads to a compact representation of the solution.
Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making.
VirtualIdentity: Privacy-Preserving User Profiling
User profiling from user generated content (UGC) is a common practice that supports the business models of many social media companies.
Scalable Structure Learning for Probabilistic Soft Logic
We introduce a greedy search-based algorithm and a novel optimization method that trade-off scalability and approximations to the structure learning problem in varying ways.
