Related papers: Post-hoc Provider Fairness Adaptation via Hierarch…

We introduce a new family of techniques to post-process ("wrap") a black-box classifier in order to reduce its bias. Our technique builds on the recent analysis of improper loss functions whose optimization can correct any twist in…

The Parameter-Efficient Fine-Tuning (PEFT) methods have been extensively researched for large language models in downstream tasks. Among all the existing approaches, the Low-Rank Adaptation (LoRA) has gained popularity for its streamlined…

Demographic skews in human preference data propagate systematic unfairness through reward models into aligned LLMs. We introduce Fairness Aware Reward Optimization (Faro), an in-processing framework that trains reward models under…

Personalized federated learning (PFL) tailors models to clients' unique data distributions while preserving privacy. However, existing aggregation-weight-based PFL methods often struggle with heterogeneous data, facing challenges in…

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a widely adopted strategy for adapting pre-trained Large Language Models (LLMs) to downstream tasks, significantly reducing memory and computational costs. However, most…

Embedding-based Retrieval Models (ERMs) have emerged as a promising framework for large-scale text retrieval problems due to powerful large language models. Nevertheless, fine-tuning ERMs to reach state-of-the-art results can be expensive…

Point-of-interest (POI) recommendation considers spatio-temporal factors like distance, peak hours, and user check-ins. Given their influence on both consumer experience and POI business, it's crucial to consider fairness from multiple…

Ranking plays a central role in connecting users and providers in Information Retrieval (IR) systems, making provider-side fairness an important challenge. While recent research has begun to address fairness in ranking, most existing…

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability…

Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large foundational models to specific tasks, particularly as model sizes continue to grow exponentially. Among PEFT methods, Low-Rank Adaptation (LoRA)…

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first…

Catastrophic forgetting is a well-documented challenge in model fine-tuning, particularly when the downstream domain has limited labeled data or differs substantially from the pre-training distribution. Existing parameter-efficient…

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social…

Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge.…

Ranking systems in web search and recommendation allocate attention among items and providers, and therefore need to balance relevance-based effectiveness with provider fairness. Existing fair-ranking methods commonly focus on exposure…

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying…

Foundation models excel across diverse tasks, but adapting them to specialized applications often requires fine-tuning, an approach that is memory and compute-intensive. Parameter-efficient fine-tuning (PEFT) methods mitigate this by…