Papers by Yaqian Zhou

Iterative GNN-based Decoder for Question Generation (2021.emnlp-main)

Copied to clipboard

Challenge:	Existing models ignore the rich structure information that is hidden in the previously generated text.
Approach:	They propose to model the previous generation using a Graph Neural Network at each decoding step.
Outcome:	The proposed model outperforms the state-of-the-art models with sentence-level QG tasks on SQUAD and MARCO datasets.

CAMIEval: Enhancing NLG Evaluation through Multidimensional Comparative Instruction-Following Analysis (2025.naacl-long)

Copied to clipboard

Ziyue Fan, Junliang He, Li Xiaoqing, Shaohui Kuang, Kai Song, Yaqian Zhou, Xipeng Qiu

Text Generation

Challenge:	Evaluating the quality of texts generated by language models has always been a challenging task in natural language processing (NLP).
Approach:	They propose a multidimensional comparative evaluation method based on instruction-following that combines relevance, factuality, and adherence with a concrete Chain-of-Thoughts process to enhance the accuracy of evaluations.
Outcome:	The proposed method outperforms existing methods in correlation with human evaluations on two NLG evaluation benchmarks.

MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time (2025.findings-naacl)

Copied to clipboard

Mozhi Zhang, Pengyu Wang, Chenkun Tan, Mianqiu Huang, Dong Zhang, Yaqian Zhou, Xipeng Qiu

Language Models

Challenge:	Existing methods to align large language models with human preferences often result in a static alignment that cannot account for the diversity of human preferences in practical applications.
Approach:	They propose a method to help large language models dynamically align with various explicit or implicit preferences specified at inference time.
Outcome:	The proposed method can help LLMs dynamically align with various explicit or implicit preferences specified at the inference stage, validating the feasibility of MetaAlign.

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLMs (2025.findings-emnlp)

Copied to clipboard

Chenkun Tan, Pengyu Wang, Shaojun Zhou, Botian Jiang, Zhaowei Li, Dong Zhang, Xinghao Wang, Yaqian Zhou, Xipeng Qiu

Multimodality

Challenge:	Recent advances in multimodal large language models focus on improving performance . however, language prior conflict leads to suboptimal vision-language alignment .
Approach:	They propose a method to decouple the alignment process from language prior interference . they use a proxy LLM to detach from language interference during pretraining .
Outcome:	The proposed method improves training performance and generalizes training data.

FiNE: Filtering and Improving Noisy Data Elaborately with Large Language Models (2025.naacl-long)

Copied to clipboard

Junliang He, Ziyue Fan, Shaohui Kuang, Li Xiaoqing, Kai Song, Yaqian Zhou, Xipeng Qiu

Language Models

Challenge:	Currently, there are two mainstream methods for improving data integrity: data filtering and data augmentation.
Approach:	They propose a method to improve data integrity by combining data filtering and data augmentation with LLMs.
Outcome:	The proposed method surpasses the open-source chat version on HalluQA by 8.45 on the open source version.

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities (2023.findings-emnlp)

Copied to clipboard

Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, Xipeng Qiu

Multimodality

Challenge:	Existing multi-modal large language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer.
Approach:	They propose a large language model with intrinsic cross-modal conversational abilities . they construct a cross-text speech instruction dataset and employ a three-stage training strategy .
Outcome:	The proposed model can follow cross-modal human instructions and handle multiple modalities with one model.

DUB: Discrete Unit Back-translation for Speech Translation (2023.findings-acl)

Copied to clipboard

Dong Zhang, Rong Ye, Tom Ko, Mingxuan Wang, Yaqian Zhou

Speech & Audio in NLP

Challenge:	Discrete unit back-translation (DUB) is a back-translated speech-to-text translation (ST) technique that can be applied to ST . a modality gap between speech and text makes it difficult to transfer these techniques to ST due to the modality of the speech-text model.
Approach:	They propose a method to represent speech with discrete units instead of continuous features in direct ST.
Outcome:	The proposed method achieves comparable performance to existing methods that rely on large-scale external data.

Calibrating the Confidence of Large Language Models by Eliciting Fidelity (2024.emnlp-main)

Copied to clipboard

Mozhi Zhang, Mianqiu Huang, Rundong Shi, Linsen Guo, Chong Peng, Peng Yan, Yaqian Zhou, Xipeng Qiu

Language Models

Challenge:	Large language models with RLHF and RLAIF have good alignment but exhibit overconfidence post-alignment.
Approach:	They propose a plug-and-play method to estimate the confidence of large language models.
Outcome:	The proposed method has shown good calibration performance on 6 RLHF-LMs on four MCQA datasets.

SENT: Sentence-level Distant Relation Extraction via Negative Training (2021.acl-long)

Copied to clipboard

Ruotian Ma, Tao Gui, Linyang Li, Qi Zhang, Xuanjing Huang, Yaqian Zhou

Information Extraction & Text Mining

Challenge:	Existing methods for relation extraction use bag labels, which introduce noise, to train the model.
Approach:	They propose to use negative training to train a model using complementary labels to separate the noisy data from the training data.
Outcome:	The proposed method improves on previous methods on sentence-level evaluation and de-noise effect.

A Relation-Oriented Clustering Method for Open Relation Extraction (2021.emnlp-main)

Copied to clipboard

Jun Zhao, Tao Gui, Qi Zhang, Yaqian Zhou

Information Extraction & Text Mining

Challenge:	Existing methods for open relation extraction (OpenRE) are designed for predefined relations, which cannot deal with new emerging relations in the real world.
Approach:	They propose a relation-oriented clustering model that leverages readily available labeled data to learn a relationship-oriented representation.
Outcome:	The proposed model reduces error rate by 29.2% and 15.7% on two datasets compared with current SOTA methods.

Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning (D18-1)

Copied to clipboard

Yucheng Wang, Zhongyu Wei, Yaqian Zhou, Xuanjing Huang

Challenge:	Existing systems for automatic essay scoring are trained to predict the score of each essay at a time without considering rating schema.
Approach:	They propose a reinforcement learning framework that incorporates quadratic weighted kappa as guidance to optimize the scoring system.
Outcome:	Experiments on benchmark datasets show the proposed framework is effective.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.