Dr Shuxiang Cao

Abstract:

Large language models (LLMs) excel in generating unstructured text. However, they struggle with producing structured output while maintaining accuracy in zero-shot information extraction (IE), such as named entity recognition (NER) and relation extraction (RE). To address these challenges, we propose CROSSAGENTIE, a multi-agent framework that enhances zero-shot IE through multi-agent LLM collaboration. CROSSAGENTIE refines LLM predictions iteratively through two mechanisms: intra-group cross-type debate, which resolves entity-label conflicts through context-based evidence and confidence aggregation, and inter-group cross-task debate, where NER and RE mutually refine outputs via bidirectional feedback. Furthermore, we introduce template finetuning, distilling high-confidence multi-agent outputs into a single model, significantly reducing inference costs while preserving accuracy. Experiments across five NER and five RE datasets show that CROSSAGENTIE significantly outperforms state-of-the-art zero-shot baselines by a large margin. CROSSAGENTIE effectively addresses LLM limitations in structured prediction with an effective and efficient approach for zero-shot information extraction. Our GitHub can be found at https://github.com/Luca/CorssAgentIE.

Abstract:

A qutrit represents a three-level quantum system, so that one qutrit can encode more information than a qubit, which corresponds to a two-level quantum system. This work investigates the potential of qutrit circuits in machine learning classification applications. We propose and evaluate different data-encoding schemes for qutrits, and find that the classification accuracy varies significantly depending on the used encoding. We therefore propose a training method for encoding optimization that allows to consistently achieve high classification accuracy, and show that it can also improve the performance within a data re-uploading approach. Our theoretical analysis and numerical simulations indicate that the qutrit classifier can achieve high classification accuracy using fewer components than a comparable qubit system. We showcase the qutrit classification using the encoding optimization method on a superconducting transmon qutrit, demonstrating the practicality of the proposed method on noisy hardware. Our work demonstrates high-precision ternary classification using fewer circuit elements, establishing qutrit quantum circuits as a viable and efficient tool for quantum machine learning applications.