Related papers: Open-Domain Safety Policy Construction
Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent boundary-case performance and high inference costs. Training…
Prompt-based pre-trained language models (PLMs) paradigm have succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimization methods require expert knowledge to design the base…
During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…
Motion control algorithms in the presence of pedestrians are critical for the development of safe and reliable Autonomous Vehicles (AVs). Traditional motion control algorithms rely on manually designed decision-making policies which neglect…
As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existing systems suffer from limited analytical depth due to reliance on abstracts and…
Large, general purpose language models have demonstrated impressive performance across many different conversational domains. While multi-domain language models achieve low overall perplexity, their outputs are not guaranteed to stay within…
The rapid expansion of scholarly publications across diverse disciplines has made it increasingly difficult to systematically evaluate how research contributes to the United Nations Sustainable Development Goals (SDGs). Domain…
Data extracted from software repositories is used intensively in Software Engineering research, for example, to predict defects in source code. In our research in this area, with data from open source projects as well as an industrial…
One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an…
The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined policies that dictate information disclosure based on context. While ensuring adherence to these…
Cross-domain recommendation (CDR) has been proven as a promising way to alleviate the cold-start issue, in which the most critical problem is how to draw an informative user representation in the target domain via the transfer of user…
Click-through rate (CTR) prediction tasks play a pivotal role in real-world applications, particularly in recommendation systems and online advertising. A significant research branch in this domain focuses on user behavior modeling. Current…
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To…
Censorship of the Internet is widespread around the world. As access to the web becomes increasingly ubiquitous, filtering of this resource becomes more pervasive. Transparency about specific content that citizens are denied access to is…
This paper tackles \textbf{open-ended deep research (OEDR)}, a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research…
Local differential privacy (LDP) is a recently proposed privacy standard for collecting and analyzing data, which has been used, e.g., in the Chrome browser, iOS and macOS. In LDP, each user perturbs her information locally, and only sends…
The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, often…
Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy…
Deep Research Agents (DRAs) can autonomously conduct complex investigations and generate comprehensive reports, demonstrating strong real-world potential. However, existing evaluations mostly rely on close-ended benchmarks, while open-ended…
A significant challenge to training accurate deep learning models on privacy policies is the cost and difficulty of obtaining a large and comprehensive set of training data. To address these challenges, we present Calpric , which combines…