Abstract:This work presents a novel approach called oracle-checker scheme for evaluating the answer given by a generative large language model (LLM). Two types of checkers are presented. The first type of checker follows the idea of property testing. The second type of checker follows the idea of program checking. Their applications are demonstrated in two separate contexts, entity extraction and paraphrase decision, respectively.
Abstract:With the availability of large language models, there is a growing interest for semiconductor chip design companies to leverage the technologies. For those companies, deployment of a new methodology must include two important considerations: confidentiality and scalability. In this context, this work tackles the problem of knowledge graph construction from hardware-design domain texts. We propose an oracle-checker scheme to leverage the power of GPT3.5 and demonstrate that the essence of the problem is in distillation of domain expert's background knowledge. Using RISC-V unprivileged ISA specification as an example, we explain key ideas and discuss practicality of our proposed oracle-checker approach.




Abstract:An analytic process is iterative between two agents, an analyst and an analytic toolbox. Each iteration comprises three main steps: preparing a dataset, running an analytic tool, and evaluating the result, where dataset preparation and result evaluation, conducted by the analyst, are largely domain-knowledge driven. In this work, the focus is on automating the result evaluation step. The underlying problem is to identify plots that are deemed interesting by an analyst. We propose a methodology to learn such analyst's intent based on Generative Adversarial Networks (GANs) and demonstrate its applications in the context of production yield optimization using data collected from several product lines.




Abstract:In this paper, we proposed VeSC-CoL (Version Space Cardinality based Concept Learning) to deal with concept learning on extremely imbalanced datasets, especially when cross-validation is not a viable option. VeSC-CoL uses version space cardinality as a measure for model quality to replace cross-validation. Instead of naive enumeration of the version space, Ordered Binary Decision Diagram and Boolean Satisfiability are used to compute the version space. Experiments show that VeSC-CoL can accurately learn the target concept when computational resource is allowed.