Papers by Lexin Zhou
DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. |
| Approach: | They propose a controllable data synthesis framework based on variational autoencoder which leverages diffusion models to reserve more information of original distribution and format structure in the learned latent distribution. |
| Outcome: | The proposed framework generates high-quality data with performance exceeding that of real data by 2%–7% on seven real-world datasets. |
An LLM Feature-based Framework for Dialogue Constructiveness Assessment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on dialogue constructiveness assessment focus on analysing conversational factors that influence individuals to take specific actions, win debates, change their perspectives or broaden their open-mindedness. |
| Approach: | They propose an LLM feature-based framework for dialogue constructiveness assessment that combines the strengths of feature- and neural approaches while mitigating their downsides. |
| Outcome: | The proposed framework outperforms standard feature-based models and neural models on three dialogue constructiveness datasets. |
PredictaBoard: Benchmarking LLM Score Predictability (2025.findings-acl)
Copied to clipboard
Lorenzo Pacchiardi, Konstantinos Voudouris, Ben Slater, Fernando Martínez-Plumed, Jose Hernandez-Orallo, Lexin Zhou, Wout Schellaert
| Challenge: | Large Language Models (LLMs) fail unpredictably, demonstrating inconsistent success in even basic common sense reasoning tasks. |
| Approach: | They propose a framework to evaluate the ability of score predictors to anticipate LLM errors on specific task instances from existing datasets. |
| Outcome: | The proposed framework evaluates the ability of score predictors to anticipate LLM errors on specific task instances from existing datasets. |
Exploring the Choice Behavior of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly being adopted across various domains where they help to make choices. |
| Approach: | They construct a virtual QA platform that includes three different experimental conditions, with four models from GPT and Llama series participating in repeated experiments. |
| Outcome: | The proposed model includes three experimental conditions and four models from GPT and Llama series. |