Papers by Hengyi Cai

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight (2020.acl-main)

Copied to clipboard

Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin

Dialogue Systems & Conversational Agents

Challenge:	Current state-of-the-art neural dialogue models learn from human conversations . however, due to the open-ended nature of human conversations, the quality of training data varies .
Approach:	They propose a data manipulation framework to augment and highlight effective training samples . they also propose to increase its manipulation skills through gradient descent with validation samples a reshaping framework to proactively restructure the data distribution towards reliable samples is also proposed .
Outcome:	The proposed framework improves the performance of open-domain neural dialogue models with respect to evaluation metrics and human judgments.

Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)

Copied to clipboard

Hao Sun, Hengyi Cai, Yuchen Li, Xuanbo Fan, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Responsible & Trustworthy NLP

Challenge:	Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers.
Approach:	They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process.
Outcome:	The proposed framework outperforms existing methods on five datasets.

Group-wise Contrastive Learning for Neural Dialogue Generation (2020.findings-emnlp)

Copied to clipboard

Hengyi Cai, Hongshen Chen, Yonghao Song, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Xiaofang Zhao

Semantic Text Processing

Challenge:	Existing approaches to training dialogue models have low diversity in open-domain contexts . prior art suggests that naive MLE objective is not effective enough .
Approach:	They propose to incorporate contrastive learning into dialogue generation by using a pretrained baseline model as a reference.
Outcome:	The proposed framework is suited for training a wide range of dialogue generation models with favorable performance over baseline training approaches.

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

Language Models

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)

Copied to clipboard

Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Responsible & Trustworthy NLP

Challenge:	Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost .
Approach:	They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs .
Outcome:	The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead.

Adaptive Parameterization for Neural Dialogue Generation (D19-1)

Copied to clipboard

Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Dawei Yin

Dialogue Systems & Conversational Agents

Challenge:	Existing models of open-domain dialogue generate responses based on sequence-to-sequence paradigms.
Approach:	They propose an Adaptive Neural Dialogue generation model which manages various conversations with conversation-specific parameterization.
Outcome:	The proposed model performs better on a large-scale conversational dataset.

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection (2024.emnlp-main)

Copied to clipboard

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Information Retrieval

Challenge:	Large language models (LLMs) often produce factually incorrect information, also known as hallucination.
Approach:	They propose a framework for verifiable text generation with evolving memory and self-reflection that incorporates long-term memory to retain documents and recent documents.
Outcome:	The proposed framework outperforms baselines on five datasets across three knowledge-intensive tasks.

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching (2026.acl-long)

Copied to clipboard

Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, Dawei Yin

Reasoning

Challenge:	Existing reinforcement learning methods rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory.
Approach:	They propose a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation.
Outcome:	The proposed framework surpasses the majority of 8B competitors on three benchmarks.

Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Changle Qu, Sunhao Dai, Hengyi Cai, Yiyang Cheng, Jun Xu, Shuaiqiang Wang, Dawei Yin

Information Retrieval

Challenge:	Existing efforts to estimate document utility rely on downstream generation performance, which conflates the influence of external documents with the intrinsic knowledge of the LLM.
Approach:	They propose an uplift-based definition of document utility that quantifies each document’s marginal benefit over the LLM’s internal knowledge.
Outcome:	The proposed framework improves the performance of the LLM by incorporating external retrieved documents into the model.

CTR-Guided Generative Query Suggestion in Conversational Search (2025.emnlp-industry)

Copied to clipboard

Erxue Min, Hsiu-Yuan Huang, Xihong Yang, Min Yang, Xin Jia, Yunfang Wu, Hengyi Cai, Junfeng Wang, Shuaiqiang Wang, Dawei Yin

Natural Language Interfaces

Challenge:	Generating effective query suggestions requires aligning model outputs with user click preferences.
Approach:	They propose a generative framework that leverages click modeling to denoise implicit feedback and enables reliable preference optimization for improving real-world user engagement.
Outcome:	The proposed framework outperforms strong baselines in CTR, relevance, diversity and diversity.

Answering Ambiguous Questions via Iterative Prompting (2023.acl-long)

Copied to clipboard

Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

Language Models

Challenge:	Empirical studies show that AmbigPrompt achieves state-of-the-art or competitive results while using less memory and having a lower inference latency than competing approaches.
Approach:	They propose an answering model with a prompting model to address imperfections in open-domain question answering . Empirical studies show AmbigPrompt achieves state-of-the-art or competitive results .
Outcome:	The proposed framework improves on two commonly-used open benchmarks and achieves state-of-the-art or competitive results while using less memory and having a lower inference latency.