Related papers: Mobile GUI Agent Privacy Personalization with Traj…
While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is…
Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of…
A core challenge for autonomous LLM agents in collaborative settings is balancing robust privacy understanding and preservation alongside task efficacy. Existing privacy benchmarks only focus on simplistic, single-turn interactions where…
Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn…
Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…
The growing number of Large Language Models (LLMs) with diverse capabilities and response styles provides users with a wider range of choices, which presents challenges in selecting appropriate LLMs, as user preferences vary in terms of…
Users' interaction or preference data used in recommender systems carry the risk of unintentionally revealing users' private attributes (e.g., gender or race). This risk becomes particularly concerning when the training data contains user…
Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all…
What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that existing preference-alignment approaches largely rely on binary pairwise comparisons, overlooking…
Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives…
Large Language Models (LLMs) excel at producing broadly relevant text, but this generality becomes a limitation when user-specific preferences are required, such as recommending restaurants or planning travel. In these scenarios, users…
A fundamental tension exists between the demand for sophisticated AI assistance in web search and the need for user data privacy. Current centralized models require users to transmit sensitive browsing data to external services, which…
As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…
Differential privacy (DP) is the standard for privacy-preserving analysis, and introduces a fundamental trade-off between privacy guarantees and model performance. Selecting the optimal balance is a critical challenge that can be framed as…
When the quality of naive prompts is carefully optimized by human experts, the task performance of large language models (LLMs) can be significantly improved. However, expert-based prompt optimizations are expensive. Herein, some works have…
Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design.…
Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scalar scores. We view generation as tracing a semantic…
Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Yet, these data contain sensitive information…
In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback…
Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the…