Papers by Wen Yin

Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities (2026.acl-long)

Copied to clipboard

Chi-Min Chan, Yujin Zhou, Pengcheng Wen, Boqin Yin, Jiaming Ji, Juntao Dai, Wei Xue, Sirui Han, Yike Guo

Challenge:	Existing evaluation benchmarks for ORMs are largely text-centric or limited to bimodal tasks . a new study examines the effectiveness of Omni-RewardBench for ORms across modalities .
Approach:	They propose a hybrid automatic-annotation and human-verification pipeline to construct high-quality evaluation data.
Outcome:	The proposed model is the first benchmark for comprehensive evaluation of ORMs across modalities.

Improve Language Model and Brain Alignment via Associative Memory (2025.findings-acl)

Copied to clipboard

Congchi Yin, Yongpeng Zhang, Xuyun Wen, Piji Li

Language Models

Challenge:	Existing studies have shown that associative memory is essential for language comprehension and comprehension.
Approach:	They propose to integrate associative memory into language models to improve alignment . they find alignment is improved in brain regions closely related to associativ memory processing .
Outcome:	The proposed model improves in brain regions closely related to associative memory processing.

IterAlign: Iterative Constitutional Alignment of Large Language Models (2024.naacl-long)

Copied to clipboard

Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, Wei Wang

Semantic Text Processing

Challenge:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness.
Approach:	They propose a data-driven constitution discovery and self-alignment framework called IterAlign to overcome these drawbacks by leveraging red teaming to uncover weaknesses of an LLM.
Outcome:	Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty by up to 13.5%.

SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs (2025.findings-emnlp)

Copied to clipboard

Zhiqiang Liu, Enpei Niu, Yin Hua, Mengshu Sun, Lei Liang, Huajun Chen, Wen Zhang

Multimodality

Challenge:	Existing evaluations for Structured Knowledge (SK) understanding are non-rigorous and focus on a single type of SK.
Approach:	They propose a structured knowledge understanding benchmark that includes four widely used structured knowledge forms.
Outcome:	The proposed benchmark is based on four widely used structured knowledge forms . it includes a question, an answer, positive knowledge units, and noisy knowledge units .

Noise-powered Multi-modal Knowledge Graph Representation Framework (2025.coling-main)

Copied to clipboard

Zhuo Chen, Yin Fang, Yichi Zhang, Lingbing Guo, Jiaoyan Chen, Jeff Z. Pan, Huajun Chen, Wen Zhang

Semantic Text Processing

Challenge:	Current efforts to integrate MMKG with pretraining are scarce.
Approach:	They propose a method that integrates multi-modal entity features into MMKGs using a Transformer-based architecture equipped with modality-level noise masking.
Outcome:	The proposed method achieves SOTA performance across ten datasets.

Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)

Copied to clipboard

Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang

Semantic Text Processing

Challenge:	Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates.
Approach:	They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters.
Outcome:	The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment.

A Neural Citation Count Prediction Model based on Peer Review Text (D19-1)

Copied to clipboard

Siqing Li, Wayne Xin Zhao, Eddy Jing Yin, Ji-Rong Wen

Semantic Text Processing

Challenge:	Recent studies have focused on extracting or mining useful features from the paper itself or the associated authors.
Approach:	They propose to utilize peer review data for the CCP task with a neural prediction model to learn a comprehensive semantic representation for peer review text.
Outcome:	The proposed model improves on the peer review data and hand-crafted features.

Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)

Copied to clipboard

Jiali Zeng, Jinsong Su, Huating Wen, Yang Liu, Jun Xie, Yongjing Yin, Jianqiang Zhao

Text Generation

Challenge:	Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model.
Approach:	They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains.
Outcome:	The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks.

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Copied to clipboard

Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

Language Models

Challenge:	Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach:	They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome:	The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.

Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering (2024.findings-acl)

Copied to clipboard

Yichi Zhang, Zhuo Chen, Yin Fang, Yanxi Lu, Li Fangming, Wen Zhang, Huajun Chen

Natural Language Interfaces

Challenge:	Domain-specific question answering (QA) requires a comprehensive understanding of a specific domain to answer specialized questions.
Approach:	They propose a new alignment objective to align the LLM preference with different human preferences uniformly to optimize LLM performance in real-world, domain-specific QA settings.
Outcome:	The proposed pipeline is superior for real-scenario domain-specific question answering with LLMs.

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

Multimodality

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

NetSafe: Exploring the Topological Safety of Multi-agent System (2025.findings-acl)

Copied to clipboard

Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, Yang Wang

Challenge:	Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications.
Approach:	They propose a framework that unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
Outcome:	The proposed framework unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.

All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)

Copied to clipboard

Le Qi, Yu Zhang, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu

Reasoning

Challenge:	Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously.
Approach:	They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion.
Outcome:	The proposed approach outperforms strong baseline models on two standard benchmarks.

CaM-HG: Causal-Enhanced MoE and Hypergraphs Network for Incomplete Multimodal Emotion Recognition in Conversations (2026.findings-acl)

Copied to clipboard

Mingjian Yang, Yong Wang, Peng Liu, Wen Yin

Dialogue Systems & Conversational Agents

Challenge:	Existing methods that focus on statistical reconstruction often fail to bridge these gaps, effectively leaving semantic holes.
Approach:	They propose a Causal-Enhanced Mixture-of-Experts and Hypergraph Network to bridge missing features . they use experts to synthesize missing features that are realistic and causally consistent .
Outcome:	The proposed model synthesizes missing features that are realistic and causally consistent . it surpasses benchmarks on IEMOCAP, CMU-MOSI, and CMU MOSEI by 1.43% and 1.25% .

Natural Language to Code Generation in Interactive Data Science Notebooks (2023.acl-long)

Copied to clipboard

Pengcheng Yin, Wen-Ding Li, Kefan Xiao, Abhishek Rao, Yeming Wen, Kensen Shi, Joshua Howland, Paige Bailey, Michele Catasta, Henryk Michalewski, Oleksandr Polozov, Charles Sutton

Programming Languages in NLP

Challenge:	Data scientists use computational notebooks to perform data wrangling and analytic tasks.
Approach:	They build a benchmark program that synthesizes programs given NL intents from users by using a Python code language model.
Outcome:	The proposed model outperforms public code LMs in a dataset of 1078 code generation problems using the pandas data analysis framework in data science notebooks.

Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning (2025.findings-acl)

Copied to clipboard

Yin Hua, Zhiqiang Liu, Mingyang Chen, Zheng Fang, Chi Man Wong, Lingxiao Li, Chi Man Vong, Huajun Chen, Wen Zhang

Structured Data in NLP

Challenge:	Existing foundation models for general knowledge graph reasoning have focused on their structural aspects, with most efforts restricted to in-KG tasks.
Approach:	They propose a conditional encoding architecture that bridges the gap between textual and structural modalities, enabling seamless integration.
Outcome:	The proposed model outperforms baseline models on 28 datasets and is generalized to out-of-KG tasks.

SynPrompt: Syntax-aware Enhanced Prompt Engineering for Aspect-based Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Wen Yin, Cencen Liu, Yi Xu, Ahmad Raza Wahla, Huang Yiting, Dezhang Zheng

Language Models

Challenge:	Existing methods of prompt-tuning for Aspect-based Sentiment Analysis (ABSA) are crude and simple.
Approach:	They propose a Syntax-aware Enhanced Prompt method which mines syntactic information related to aspect words from the syntaktic dependency tree.
Outcome:	The proposed method exploits the syntactic knowledge embedded in PLMs and achieves favorable results on three benchmark datasets.

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

Semantic Text Processing

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.