Related papers: PersonaBench: Evaluating AI Models on Understandin…
Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for,…
We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user's "persona" (e.g. user profile or…
Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning \& Action-planning), a…
This work presents a systematic benchmark of differentially private synthetic data generation algorithms that can generate tabular data. Utility of the synthetic data is evaluated by measuring whether the synthetic data preserve the…
In high-stakes domains like healthcare, users often expect that sharing personal information with machine learning systems will yield tangible benefits, such as more accurate diagnoses and clearer explanations of contributing factors.…
Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To address this, differentially private synthetic data generation…
The chapter discusses the foundational impact of modern generative AI models on information access (IA) systems. In contrast to traditional AI, the large-scale training and superior data modeling of generative AI models enable them to…
Conversational assistants process personal data and must comply with data protection regulations that require providers to be transparent with users about how their data is handled. Transparency, in a legal sense, demands preciseness,…
Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle…
Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and…
The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, existing benchmarks primarily focus on daily open-domain…
Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simulates 1,000 realistic user-chatbot interactions on 300+…
Artificial Intelligence (AI) advancement is heavily dependent on access to large-scale, high-quality training data. However, in specialized domains such as healthcare, data acquisition faces significant constraints due to privacy…
Nowadays, real data in person re-identification (ReID) task is facing privacy issues, e.g., the banned dataset DukeMTMC-ReID. Thus it becomes much harder to collect real data for ReID task. Meanwhile, the labor cost of labeling ReID data is…
Data plays a pivotal role in Text-Based Person Retrieval (TBPR) research. Mainstream research paradigm necessitates real-world person images with manual textual annotations for training models, posing privacy concerns and annotation…
Generative AI models have substantially improved the realism of synthetic media, yet their misuse through sophisticated DeepFakes poses significant risks. Despite recent advances in deepfake detection, fairness remains inadequately…
Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional…
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-augmented generation…
Personality determines a wide variety of human daily and working behaviours, and is crucial for understanding human internal and external states. In recent years, a large number of automatic personality computing approaches have been…
Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. However, research in this area is often hindered…