Papers by Zhengyuan Liu

Fantastic Expressions and Where to Find Them: Chinese Simile Generation with Multiple Constraints (2023.acl-long)

Challenge:	a limited amount of data exists for human-human spoken dialogues for research and development . a dialogue comprehension system that extracts clinical information from spoken conversations is clinically useful .
Approach:	They propose a framework inspired by nurse-initiated clinical symptom monitoring conversations to construct a simulated human-human dialogue dataset.
Outcome:	The proposed system achieves more than 80% F1 on held-out test set from nurse-to-patient conversations.

Copied to clipboard

Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Xiangpeng Wei, Zhengyuan Liu, Jun Xie

Information Retrieval

Challenge:	Existing attempts to generate similes as context-free tasks are not suitable for simile generation . however, simile generated under such settings might be undesirable, we argue .
Approach:	They propose a model to generate a simile with multiple simile elements . they propose to use a vehicle retrieval module to obtain the explicable comparison .
Outcome:	The proposed model can generate a simile with multiple simile elements, e.g., context and vehicle.

Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems (2024.emnlp-main)

Copied to clipboard

Zhengyuan Liu, Stella Yin, Geyu Lin, Nancy Chen

Dialogue Systems & Conversational Agents

Challenge:	Existing large language models (LLMs) can be adopted as tutoring agents for math and language learning.
Approach:	They propose a framework to construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personality-aware student simulation in a language learning scenario.
Outcome:	The proposed framework can construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personality-aware student simulation in a language learning scenario.

In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Ayrton Joaquin, Bin Wang, Zhengyuan Liu, Philippe Muller, Nicholas Asher, Brian Lim, Nancy Chen

SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning (2025.acl-industry)

Challenge:	Large Language Models (LLMs) exhibit surprising abilities across a variety of language tasks.
Approach:	They propose an algorithm which selects a coreset by analyzing correlation between training and evaluation samples with a trained model.
Outcome:	The proposed algorithm can achieve similar performance with just 50% of the training data while preserving the accuracy of the existing model.

Copied to clipboard

Zhengyuan Liu, Geyu Lin, Hui Li Tan, Huayun Zhang, Yanfeng Lu, Xiaoxue Gao, Stella Xin Yin, Sun He, Hock Huan Goh, Lung Hsiang Wong, Nancy F. Chen

AudioBench: A Universal Benchmark for Audio Large Language Models (2025.naacl-long)

Challenge:	Empirical studies show that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels.
Approach:	They propose a dialogic tutor designed to facilitate language learning through picture description tasks.
Outcome:	Empirical studies show that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels.

Copied to clipboard

Bin Wang, Xunlong Zou, Geyu Lin, Shuo Sun, Zhuohan Liu, Wenyu Zhang, Zhengyuan Liu, AiTi Aw, Nancy F. Chen

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment (2026.acl-long)

Challenge:	Existing evaluation regimes for audio large language models do not cover the breadth of their possible use cases.
Approach:	They propose to use AudioBench to evaluate audio large language models . they found that no single model excels consistently across all tasks .
Outcome:	The proposed evaluation targets speech understanding, audio scene understanding, and voice understanding (paralinguistic) . no single model excels consistently across all tasks, the paper found .

Copied to clipboard

Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee

Resilience of Large Language Models for Noisy Instructions (2024.findings-emnlp)

Challenge:	Current alignment paradigms treat "human values" as a monolithic entity, ignoring the fact that many societies are a mosaic of diverse subgroups with distinct and sometimes conflicting values, preferences, and norms.
Approach:	They examine whether Large Language Models can emulate distinct cultural values of subgroups . they use a global value survey to examine the value landscape of a multicultural society .
Outcome:	The proposed model improves on unseen, out-of-distribution subgroups by 17.4% . the model widens the disparity between subgroup groups when measured by distance-aware metrics.

Copied to clipboard

Bin Wang, Chengwei Wei, Zhengyuan Liu, Geyu Lin, Nancy Chen

Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts (2025.findings-acl)

Challenge:	Large language models (LLMs) are powerful tools for interpreting human commands and generating text.
Approach:	They examine the resilience of large language models against five common types of disruptions including ASR, OCR, grammatical errors, typographical errors and distractive content.
Outcome:	The models show resistance to noise, but their performance suffers . authors evaluated the models against five common types of disruptions based on their results .

Copied to clipboard

Quanyu Long, Jianda Chen, Zhengyuan Liu, Nancy F. Chen, Wenya Wang, Sinno Jialin Pan

Information Retrieval

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks.
Approach:	They propose a tri-encoder sequential retriever that models a Markov Decision Process (MDP) this method decomposes the probability of retrieving a set of elements into a sequence of conditional probabilities and allows each retrieval step to be conditioned on previously selected examples.
Outcome:	The proposed method outperforms baselines and shows that it can handle multiple pieces of evidence or examples.

Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization (2020.findings-emnlp)

Copied to clipboard

Zhengyuan Liu, Ke Shi, Nancy Chen

Text Generation

Challenge:	Recent advances in text summarization have overcome position bias in news articles . however, there are long-standing, unresolved challenges in extractive summarizing .
Approach:	They propose a neural framework that can flexibly control summary generation by introducing a set of sub-aspect functions.
Outcome:	The proposed framework can flexibly control summary generation by introducing sub-aspect functions . extracted summaries with minimal position bias are comparable with standard models .

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen

Exploring Self-supervised Logic-enhanced Training for Large Language Models (2024.naacl-long)

Challenge:	Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach:	They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome:	The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .

Copied to clipboard

Fangkai Jiao, Zhiyang Teng, Bosheng Ding, Zhengyuan Liu, Nancy Chen, Shafiq Joty

N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking (2022.findings-acl)

Challenge:	Traditional attempts to enhance the logical reasoning abilities of language models often rely on supervised fine-tuning, limiting their generalization to new tasks or domains.
Approach:	They propose a framework for integrating logical reasoning capabilities into LLMs and activating them via in-context learning.
Outcome:	The proposed framework achieves comparable results to existing models on three language understanding benchmarks.

Copied to clipboard

Ibrahim Aksu, Zhengyuan Liu, Min-Yen Kan, Nancy Chen

Dialogue Systems & Conversational Agents

Challenge:	augmentation of task-oriented dialogues has followed standard methods for plain-text despite its richly annotated structure.
Approach:	They propose an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner.
Outcome:	The proposed framework performs better on seen values and more robust to unseen values on n-shot training scenarios.

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation (2025.findings-emnlp)

Copied to clipboard

Zheng Weihua, Roy Ka-Wei Lee, Zhengyuan Liu, Wu Kui, AiTi Aw, Bowei Zou

Controllable Neural Dialogue Summarization with Personal Named Entity Planning (2021.emnlp-main)

Challenge:	Multilingual Large Language Models (MLLMs) exhibit strong generalization across languages, yet they remain prone to hallucinations due to training data imbalances.
Approach:	They propose a cross-lingual Chain-of-Thought framework that enhances cross-linguistic alignment . the framework guides the model to reason in a high-resource language before generating answers in low-resourced language.
Outcome:	The proposed framework reduces hallucination rates by up to 62% and significantly improves factual knowledge transfer across language pairs.

Copied to clipboard

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that our proposed framework generates fluent and factually consistent summaries under various planning controls using both objective metrics and human evaluations.
Approach:	They propose a controllable neural generation framework that can guide dialogue summarization with personal named entity planning.
Outcome:	The proposed framework generates fluent and factually consistent summaries under various planning controls using objective metrics and human evaluations.

Multilingual Neural RST Discourse Parsing (2020.coling-main)

Copied to clipboard

Zhengyuan Liu, Ke Shi, Nancy Chen

Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD (2025.emnlp-main)

Challenge:	Existing studies on text discourse parsing for English are limited due to the lack of annotated data.
Approach:	They propose to use multilingual vector representations and segment-level translation to establish a neural, cross-lingual discourse parser.
Outcome:	The proposed model achieves state-of-the-art on cross-lingual, document-level discourse parsing on all sub-tasks.

Copied to clipboard

Bryan Chen Zhengyu Tan, Daniel Wai Kit Chin, Zhengyuan Liu, Nancy F. Chen, Roy Ka-Wei Lee

Joint Dialogue Topic Segmentation and Categorization: A Case Study on Clinical Spoken Conversations (2023.emnlp-industry)

Challenge:	Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues.
Approach:	They propose a framework evaluating multi-turn stance-change dynamics across dual dimensions: persuasion type and domain.
Outcome:	The proposed framework improves LLM-3.1-8B-Instruct accuracy under misleading persuasion in safety contexts from 4.21% to 76.54%.

Copied to clipboard

Zhengyuan Liu, Siti Umairah Md Salleh, Hong Choon Oh, Pavitra Krishnaswamy, Nancy Chen

Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension (P19-1)

Challenge:	Utilizing natural language processing in clinical conversations is effective to improve the efficiency of workflows for medical staff and patients.
Approach:	They propose a model for dialogue segmentation and topic categorization that integrates natural language processing techniques into a joint model.
Outcome:	The proposed model improves on follow-up calls for diabetes management and reduces computational complexity and cost.

Copied to clipboard

DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation (2025.coling-main)

Challenge:	Existing research on multi-turn spoken conversations focuses on reading comprehension of passages . interactivity of spoken content can cause lower information density and topic diffusion .
Approach:	They propose a hierarchical attention neural network architecture to improve spoken dialogue comprehension by combining turn-level and word-level attention mechanisms.
Outcome:	The proposed approach outperforms baseline attention models and is robust to lengthy and out-of-distribution test samples.

Copied to clipboard

Minzhi Li, Zhengyuan Liu, Shumin Deng, Shafiq Joty, Nancy Chen, Min-Yen Kan

DeepRTL2: A Versatile Model for RTL-Related Tasks (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are scalable and economical evaluators, but how reliable they are is still under-explored.
Approach:	They propose a framework which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices and provides an interpretable window for how well LLMs evaluate .
Outcome:	The proposed framework improves performance on a variety of meta-evaluation benchmarks by providing an interpretable window for how well LLMs evaluate .

Copied to clipboard

Yi Liu, Hongji Zhang, Yunhao Zhou, Zhengyuan Shi, Changran Xu, Qiang Xu

BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models (2026.eacl-long)

Challenge:	Integration of large language models into electronic design automation has been a key driver in eDA.
Approach:	They propose a family of large language models that unifies generation- and embedding-based tasks related to RTL.
Outcome:	The proposed model achieves state-of-the-art performance across all evaluated tasks.

Copied to clipboard

Bryan Chen Zhengyu Tan, Weihua Zheng, Zhengyuan Liu, Nancy F. Chen, Hwaran Lee, Kenny Tsu Wei Choo, Roy Ka-Wei Lee

Robustness in NLP

Challenge:	Existing evaluations assess static recall or isolated visual grounding, leaving unanswered whether VLMs possess robust and transferable cultural understanding.
Approach:	They propose a multimodal, multicultural benchmark to evaluate the robustness of everyday cultural knowledge in vision-language models across linguistic rephrasings and visual modalities.
Outcome:	‘BLEnD-Vis‘ constructs 313 culturally grounded question templates spanning 16 regions and generates three aligned multiple-choice formats.

Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks (2020.coling-industry)

Copied to clipboard

Zhengyuan Liu, Pavitra Krishnaswamy, Ai Ti Aw, Nancy Chen

Domain-Specific Data Generation Framework for RAG Adaptation (2026.findings-acl)

Challenge:	Neural approaches have improved machine comprehension tasks, but models often operate as a black-box, resulting in lower interpretability.
Approach:	They propose a hybrid approach to quantify model uncertainty using Bayesian weight approximation and boost up inference speed by 80% relative to test time.
Outcome:	The proposed approach boosts inference speed by 80% relative to the previous approach and is applied to a clinical dialogue comprehension task.

Copied to clipboard

Chris Xing Tian, Weihao Xie, Zhen Chen, Hui Liu, Zhengyuan Yi, Haoliang Li, Shiqi Wang, Siwei Ma

Information Retrieval

Challenge:	Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses.
Approach:	They propose a scalable and modular data-centric framework for generating domain-grounded question–answer–context triples tailored to diverse RAG adaptation strategies.
Outcome:	The proposed framework generates domain-grounded question–answer–context triples for multiple RAG adaptation strategies.

Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer (2022.findings-naacl)

Copied to clipboard

Guiding Computational Stance Detection with Expanded Stance Triangle Framework (2023.acl-long)

Low-Resource NLP

Challenge:	Text style transfer is an important task in controllable language generation due to the scarcity of large-scale parallel data.
Approach:	They propose a semi-supervised framework for text style transfer that bootstraps with supervision guided by automatically constructed pseudo-parallel pairs and improves the sequence-to-sequence policy gradient via reinforcement rewards.
Outcome:	The proposed framework achieves state-of-the-art performance on multiple datasets and produces effective generation with as minimal as 10% of training data.

Copied to clipboard

Zhengyuan Liu, Yong Keong Yap, Hai Leong Chieu, Nancy Chen

Sentiment Analysis

Challenge:	Experimental results show that strategically-enriched data can significantly improve the performance on out-of-domain and cross-target evaluation.
Approach:	They propose to decompose a stance detection task from a theoretical perspective and extend it with additional annotations.
Outcome:	The proposed task improves performance on out-of-domain and cross-target evaluations using a linguistic framework.

Programming over Thinking: Efficient and Robust Multi-Constraint Planning (2026.acl-long)

Copied to clipboard

Derrick Goh Xin Deik, Quanyu Long, Zhengyuan Liu, Nancy F. Chen, Wenya Wang

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing (2024.emnlp-main)

Challenge:	Existing large language model approaches lack flexibility in multi-constraint planning . SCOPE achieves state-of-the-art performance while lowering cost and latency .
Approach:	They propose a framework that disentangles query-specific problem reasoning from generic code execution.
Outcome:	The Scalable Code Planning Engine achieves state-of-the-art performance while lowering cost and latency.

Copied to clipboard

Fangkai Jiao, Chengwei Qin, Zhengyuan Liu, Nancy Chen, Shafiq Joty

Reasoning

Challenge:	Recent studies have raised concerns regarding the hallucination and flaws in their reasoning process.
Approach:	They propose a framework to learn planning-based reasoning through Direct Preference Optimization on collected trajectories, which are ranked according to synthesized process rewards.
Outcome:	The proposed model surpasses GPT-3.5-Turbo on logical reasoning benchmarks on a set of logically-based reasoning tasks.

Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection (2023.findings-emnlp)

Copied to clipboard

Zhengyuan Liu, Hai Chieu, Nancy Chen

Sentiment Analysis

Challenge:	Existing methods for data-driven annotations require domain-specific and task-aligned supervision.
Approach:	They propose a multi-label and multi-target sampling strategy to optimize the annotation quality.
Outcome:	The proposed method significantly improves performance and learning efficacy on the benchmark stance detection corpora.

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Copied to clipboard

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Ming Gong, Lijuan Wang, Zicheng Liu, Houqiang Li, Nan Duan

CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation (2023.emnlp-main)

Challenge:	Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach:	They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome:	The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

Copied to clipboard

Minzhi Li, Taiwei Shi, Caleb Ziems, Min-Yen Kan, Nancy Chen, Zhengyuan Liu, Diyi Yang

Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)

Challenge:	Annotated data plays a critical role in training models and evaluating their performance.
Approach:	They propose a paradigm for Human-LLM co-annotation of unstructured texts at scale that utilizes uncertainty to estimate LLMs’ annotation capability.
Outcome:	The proposed model outperforms existing models on many text-annotation tasks with up to 21% performance improvement over random baseline.

Copied to clipboard

Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang

Information Extraction & Text Mining

Challenge:	CCTA reports provide an assessment of coronary disease severity to guide patient management.
Approach:	They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports .
Outcome:	The proposed approach improves the F1-score by 6%-13% compared with direct methods.

Instructive Dialogue Summarization with Query Aggregations (2023.emnlp-main)

Copied to clipboard

Bin Wang, Zhengyuan Liu, Nancy Chen

Exploiting Discourse-Level Segmentation for Extractive Summarization (D19-54)

Challenge:	Conventional dialogue summarization methods generate summaries without considering user’s specific interests.
Approach:	They propose a three-step approach to synthesize high-quality query-based summarization triples by training a unified model on three summarizing datasets with multi-purpose instructive triples.
Outcome:	The proposed model outperforms state-of-the-art models and even models with larger sizes on four datasets including dialogue summarization and dialogue reading comprehension.

Copied to clipboard

Information Extraction & Text Mining

Challenge:	Existing approaches to extract summarize text are based on sentences as the elementary unit, but semantic segments containing supplementary information or descriptive details are often nonessential in the generated summaries.
Approach:	They propose to exploit discourse-level segmentation as a finer-grained means to more precisely pinpoint the core content in a document.
Outcome:	The proposed method improves extractive summarization performance on CNN/Daily Mail dataset.

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering (2025.naacl-long)

Copied to clipboard

Chenglei Si, Yanzhe Zhang, Ryan Li, Zhengyuan Yang, Ruibo Liu, Diyi Yang

SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning (2024.naacl-long)

Challenge:	Generative AI has made rapid advances in multimodal understanding and code generation.
Approach:	They construct a first real-world benchmark for multimodal large language models that directly convert visual designs into code implementations by manually curating 484 diverse real-life webpages as test cases.
Outcome:	The proposed model can generate code implementations that directly render into the given reference webpages, given the screenshots as input.

Copied to clipboard

Bin Wang, Zhengyuan Liu, Xin Huang, Fangkai Jiao, Yang Ding, AiTi Aw, Nancy Chen

Multilinguality

Challenge:	a new benchmark for multilingual foundation models is being developed . brittleness of foundation models in the dimensions of semantics and multilinguality is a key limitation .
Approach:	They propose a benchmark for multilingual foundation models, SeaEval . they examine how well these models comprehend cultural practices, nuances, and values .
Outcome:	The proposed model can be used to evaluate multilingual and multicultural scenarios.

Shanks: Simultaneous Hearing and Thinking for Spoken Language Models (2026.acl-long)

Copied to clipboard

Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie Liu, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang

LDEDE: LRP-Driven Efficient Detection and Editing Framework for LLM Privacy Neurons (2026.findings-acl)

Challenge:	Existing large language models and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn.
Approach:	They propose a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to user input.
Outcome:	The proposed framework enhances real-time user–SLM interaction in two scenarios.

Copied to clipboard

Zhao Zhengyuan, Cao Lifeng, null Sunhaodong, Shi Haotian, Du Xuehui, Liu Aodi, Niu Lanjie, Yang Xiaocheng