Papers by Xueying Li
BeSimulator: A Large Language Model Powered Text-based Behavior Simulator (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing robot simulators focus on physical process modeling and realistic rendering, resulting in high computational costs and limited adaptability. |
| Approach: | They propose a modular and novel LLM-powered framework to analyze and validate robot behaviors in text-based environments. |
| Outcome: | The proposed framework can generalize across scenarios and achieve long-horizon complex simulation. |
MotiR: Motivation-aware Retrieval for Long-Tail Recommendation (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for retrieval of recommendation systems rely on collaborative filtering signals and lacks similarity for long-tail items. |
| Approach: | They propose a Motivation-aware Retrieval for Long-Tail Recommendation that integrates purchase motivations with traditional item features to capture similarity among long-tail items. |
| Outcome: | The proposed model captures similarity between long-tail items while maintaining collaborative filtering advantages for popular items. |
Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but their deployment in high-stake domains requires consistent and coherent behavior across multiple rounds of user interaction. |
| Approach: | They propose a framework for evaluating and improving LLM response consistency, and introduce a benchmark dataset to evaluate LLM consistency. |
| Outcome: | The proposed framework improves response stability without sacrificing accuracy, and offers a practical path toward more dependable behavior in critical, real-world deployments. |