Related papers: Trustworthy and Controllable Professional Knowledg…

Recent advances in natural language processing enable more intelligent ways to support knowledge sharing in factories. In manufacturing, operating production lines has become increasingly knowledge-intensive, putting strain on a factory's…

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation…

Due to the cost-prohibitive nature of training Large Language Models (LLMs), fine-tuning has emerged as an attractive alternative for specializing LLMs for specific tasks using limited compute resources in a cost-effective manner. In this…

Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulnerable to microarchitectural leakage, side-channel attacks,…

Accurate hardware performance models are critical to efficient code generation. They can be used by compilers to make heuristic decisions, by superoptimizers as a minimization objective, or by autotuners to find an optimal configuration for…

Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns due to sensitive data transmission and require substantial communication bandwidth, which is…

Large Language Models (LLMs) exhibit impressive problem-solving skills across many tasks, but they still underperform compared to humans in various downstream applications, such as text-to-SQL. On the BIRD benchmark leaderboard, human…

Generative AI, especially through large language models (LLMs), is transforming how technical knowledge can be accessed, reused, and extended. PETSc, a widely used numerical library for high-performance scientific computing, has accumulated…

Recent explorations of large-scale pre-trained language models (PLMs) have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, it requires tremendous computational resources…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounced in multi-tenant environments, where shared resources must…

While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this parametric knowledge is actually usable in performing downstream tasks. We propose a systematic…

The general capabilities of Large Language Models (LLM) highly rely on the composition and selection on extensive pretraining datasets, treated as commercial secrets by several institutions. To mitigate this issue, we open-source the…

Trusted Execution Environments (TEEs) are used to protect sensitive data and run secure execution for security-critical applications, by providing an environment isolated from the rest of the system. However, over the last few years, TEEs…

Despite their success at many natural language processing (NLP) tasks, large language models still struggle to effectively leverage knowledge for knowledge-intensive tasks, manifesting limitations such as generating incomplete, non-factual,…

Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world. In several domains, such as healthcare, such technology has significant potential to reduce the…

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and analyzable. By analyzing expert activation patterns in MoE large language models (LLMs), we…

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs. However, consumer-level…

Trusted Execution Environments (TEEs), such as Intel Software Guard eXtensions (SGX), are considered as a promising approach to resolve security challenges in clouds. TEEs protect the confidentiality and integrity of application code and…