Papers by Zhonghai Wu
Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Entity name matching always retrieves irrelevant facts from the view of local entity words. |
| Approach: | They propose a knowledge selection approach and a generative model that integrates commonsense knowledge into the dialogue response generation by integrating commonsensical knowledge into a query. |
| Outcome: | The proposed approach improves on the most metrics and comparable to baselines. |
Representation Learning with Ordered Relation Paths for Knowledge Graph Completion (D19-1)
Copied to clipboard
| Challenge: | Existing knowledge graphs are incomplete and lack the order of relations in paths. |
| Approach: | They propose a method which takes relation paths into account but ignores order of relations in paths which is important for reasoning. |
| Outcome: | The proposed method performs better than state-of-the-art methods on two benchmark datasets. |
Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-trained language models can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. |
| Approach: | They propose a two-stage framework to integrate a linearized knowledge into plan text using a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact. |
| Outcome: | The proposed framework improves the performance of pre-trained language models by using section-aware strategies to encode the linearized knowledge. |
KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge-enhanced methods only seek knowledge from a single source, resulting in insufficient coverage of a given knowledge source. |
| Approach: | They propose to use multiple independent decoder heads to infuse multi-source knowledge into dialogue generation more efficiently by incorporating external knowledge into the dialogue generation. |
| Outcome: | The proposed approach overcomes three challenges in infusing multi-source knowledge into dialogue generation more efficiently. |
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that EasyRL consistently outperforms state-of-the-art baselines due to the substantial annotation cost and issues such as model collapse or reward hacking. |
| Approach: | They propose a supervised RL approach with a divide-and-conquer strategy that simulates the human cognitive acquisition curve using easy labeled data. |
| Outcome: | The proposed approach outperforms state-of-the-art models on mathematical and scientific benchmarks using only 10% of easy labeled data. |
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness (2020.acl-main)
Copied to clipboard
| Challenge: | Generative dialogue systems tend to produce generic and boring responses, causing boring conversations . a novel commonsense knowledge-aware dialogue generation model is proposed to solve this problem . |
| Approach: | They propose to retrieve and introduce knowledge facts from knowledge graphs to reduce boring conversations . they use a Felicitous Fact mechanism to help the model focus on context-relevant knowledge facts . |
| Outcome: | The proposed model outperforms the state-of-the-art approach in most experiments. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |
More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-enhanced methods use a single-source homogeneous knowledge base with limited knowledge coverage. |
| Approach: | They propose a multi-source heterogeneous knowledge-enhanced dialogue generation model that leverages multiple knowledge sources to improve knowledge coverage. |
| Outcome: | The proposed model outperforms existing knowledge-enhanced models on a Chinese dataset and shows that it can leverage multiple heterogeneous knowledge sources to improve knowledge coverage. |
HL-EncDec: A Hybrid-Level Encoder-Decoder for Neural Response Generation (C18-1)
Copied to clipboard
| Challenge: | Existing models for conversation systems operate sentences at word-level . word-based models suffer from Unknown Words Issue and Preference Issue . |
| Approach: | They propose a hybrid-level Encoder-Decoder model which utilizes word-level features and character-level ones. |
| Outcome: | The proposed model outperforms non-word-level models in automatic metrics and human annotations on a Chinese corpus. |