相关论文: Policy-Governed RAG - Research Design Study

Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt of a large language model (LLM), RAG enables more reliable…

Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scattered across corporate filings. Existing retrieval-augmented…

This PhD dissertation investigates garbage-free reversible computing systems from abstract design to physical gate-level implementation. Designed in reversible logic, we propose a ripple-block carry adder and work towards a reversible…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

The spatial control of material placement afforded by metal additive manufacturing (AM) has enabled significant progress in the development and implementation of compositionally graded alloys (CGAs) for spatial property variation in…

This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior…

Retrieval Augmented Generation (RAG) has emerged as the de facto industry standard for user-facing NLP applications, offering the ability to integrate data without re-training or fine-tuning Large Language Models (LLMs). This capability…

Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external knowledge, yet conventional centralized RAG requires aggregating distributed data, raising privacy risks and incurring high retrieval latency and cost.…

We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control policy (e.g. one trained as a neural network) is paired with…

Agentic artificial intelligence (AI) shows promise for automating O-RAN wireless supervisory control, but translated intents still require an executor-side decision before live network actuation. Existing control flows lack explicit…

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…

Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG systems still produce incorrect answers in many cases. Why…

We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers a pipeline for development efficiency with tools for raw…

RAG systems are increasingly deployed in high-stakes domains where users expect outputs to be consistent across semantically equivalent queries. However, existing systems often exhibit significant inconsistencies due to variability in both…

Processing regulations and resulting requirements to achieve regulatory compliance in software engineering (SE) is a developing challenge due to the continuously growing amount, complexity, and expanding scope of regulations. Despite the…

The paper deals with the problem of output regulation of nonlinear systems by presenting a learning-based adaptive internal model-based design strategy. We borrow from the adaptive internal model design technique recently proposed in [1]…

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it…

In real-world applications of reinforcement learning (RL), noise from inherent stochasticity of environments is inevitable. However, current policy evaluation algorithms, which plays a key role in many RL algorithms, are either prone to…

The rapid rollout of AI in heterogeneous public and societal sectors has subsequently escalated the need for compliance with regulatory standards and frameworks. The EU AI Act has emerged as a landmark in the regulatory landscape. The…

The key innovation of our analytical method, CaRT, lies in establishing a new hierarchical, distributed architecture to guarantee the safety and robustness of a given learning-based motion planning policy. First, in a nominal setting, the…