Papers by Jixiong Chen
Personalized Topic Selection Model for Topic-Grounded Dialogue (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing topic-grounded dialogue systems tend to predict user-uninteresting and contextually irrelevant topics due to noise within side information sources. |
| Approach: | They propose a personalized topic selection model for topic-grounded dialogue that selectively aggregates side information to generate engaging responses. |
| Outcome: | The proposed model outperforms state-of-the-art models on multiple evaluation metrics. |
SMART: Semantic Header Flattening and Pseudo-Code-Style Reasoning for LLM-based Complex Table Question Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to complex table question answering rely on handcrafted table linearization or prompts . Existing methods rely only on hand-crafted table and require hierarchical hierarchies to align conditions, attributes, and values. |
| Approach: | They propose a framework that explicitly decouples table structure understanding from reasoning execution. |
| Outcome: | Experiments show that SMART improves accuracy and robustness of complex table question answering (TQA) . SMart decouples table structure understanding from reasoning execution, enabling state-of-the-art performance. |
Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. |
| Approach: | They propose a method to generate personalized dialogues using latent-space energy-based models by using a latent space energy-model. |
| Outcome: | The proposed method outperforms baselines in personality controllability and response quality. |