Papers by Zihan Liu

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning (2023.findings-emnlp)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

Challenge:	Existing methods for image-to-text generation store all knowledge within parameters, thus requiring computational-expensive fine-tuning.
Approach:	They propose a Retrieval-augmented Visual Language Model that stores all the knowledge within parameters and can be used to retrieve it from the external database.
Outcome:	The proposed model significantly boosts performance for image-to-text generation tasks with 4x less parameters compared with baseline methods.

Copied to clipboard

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Reasoning

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents (2025.findings-acl)

Copied to clipboard

Guhong Chen, Liyang Fan, Zihan Gong, Nan Xie, Zixuan Li, Ziqiang Liu, Chengming Li, Qiang Qu, Hamid Alinejad-Rokny, Shiwen Ni, Min Yang

Robustness in NLP

Challenge:	Existing legal language models struggle with dynamic courtroom interactions, resulting in overfitting to standardized legal tasks.
Approach:	They propose a new adversarial evolutionary approach for agents that performs dynamic knowledge learning and evolution through structured adversarials in a simulated courtroom program.
Outcome:	The proposed approach outperforms existing LLM-based models in three critical dimensions: cognitive agility, professional knowledge, and logical rigor.

Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing (2026.acl-industry)

Copied to clipboard

Chao Feng, Zihan Liu, Siddhant Gupta, Jan von der Assen

AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization (2021.naacl-main)

Challenge:	Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts.
Approach:	They propose to integrate semantic retrieval with domain-adapted large language models to support test engineers in real-world HIL workflows.
Outcome:	The proposed system improves perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs.

Copied to clipboard

Tiezheng Yu, Zihan Liu, Pascale Fung

Low-Resource NLP

Challenge:	State-of-the-art abstractive summarization models rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available.
Approach:	They propose to use domain adaptation methods to simulate the low-resource domain adaptation setting for abstractive summarization systems with existing datasets across six diverse target domains.
Outcome:	The proposed model can be used to adapt to a low-resource domain adaptation setting.

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Copied to clipboard

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition (2025.acl-long)

Copied to clipboard

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition (2024.acl-long)

Challenge:	Creating lyrics and melodies in symbolic format requires expert knowledge of melody and an advanced understanding of lyrics.
Approach:	They introduce SongComposer, a music-specialized large language model that can create symbolic lyrics and melodies following instructions.
Outcome:	The proposed model outperforms existing models in symbolic song composition tasks.

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Challenge:	Large language models (LLMs) are a promising alternative to expensive human evaluations.
Approach:	They propose a framework that iteratively aligns LLM-based evaluators with human preference . they decompose a given evaluation task into finer-grained criteria .
Outcome:	The proposed framework iteratively aligns LLM-based evaluators with human preference . it decomposes a given evaluation task into finer-grained criteria . the framework is efficient to train and more explainable than relying solely on prompts .

Copied to clipboard

Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables (D19-1)

Challenge:	Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach:	They propose a method that integrates models, data, and tasks to refine datasets.
Outcome:	The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.

Copied to clipboard

Zihan Liu, Jamin Shin, Yan Xu, Genta Indra Winata, Peng Xu, Andrea Madotto, Pascale Fung

Low-Resource NLP

Challenge:	a lack of research on multilingual or cross-lingual task-oriented dialog systems has limited results . we propose a zero-shot adaptation of task-orientated dialog systems to low-resource languages . task-focused systems are often trained with monolingual datasets that are expensive to build or acquire .
Approach:	They propose a zero-shot adaptation of multilingual task-oriented dialog systems to low-resource languages using latent variables and a set of very few parallel word pairs.
Outcome:	The proposed model performs better in natural language understanding task compared to state-of-the-art model . the proposed model uses very few parallel word pairs to refine cross-lingual representations .

HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification (2022.emnlp-main)

Copied to clipboard

Zihan Wang, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui, Houfeng Wang

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning (2025.acl-long)

Challenge:	Hierarchical text classification (HTC) is a multi-label classification problem with a complex label hierarchy.
Approach:	They propose a Hierarchy-aware Prompt Tuning method to handle HTC from a multi-label perspective using a dynamic virtual template and label words that take the form of soft prompts to fuse the label hierarchy knowledge.
Outcome:	The proposed method achieves state-of-the-art performance on 3 popular HTC datasets and is adept at handling imbalance and low resource situations.

Copied to clipboard

Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu

Challenge:	Large language models (LLMs) use tokenization methods but often obscure internal character structures within tokens.
Approach:	They propose a method that improves models’ ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer’s vocabulary.
Outcome:	Experiments show that the proposed method improves position prediction accuracy in large language models, enabling more precise identification of target characters in original text.

Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization (2021.emnlp-main)

Copied to clipboard

Tiezheng Yu, Wenliang Dai, Zihan Liu, Pascale Fung

Generalizing Question Answering System with Pre-trained Language Model Fine-tuning (D19-58)

Challenge:	Existing MAS models cannot leverage GPLMs’ powerful generation ability.
Approach:	They propose a method to construct vision guided (VG) GPLMs that incorporate visual information while maintaining their original text generation ability.
Outcome:	The proposed model outperforms the previous state-of-the-art model by 5.7 ROUGE-1, 5.3 ROUGe-2, and 5.1 ROUGEL-L scores on the How2 dataset and contributes 83.6% of the overall improvement.

Copied to clipboard

Dan Su, Yan Xu, Genta Indra Winata, Peng Xu, Hyeondey Kim, Zihan Liu, Pascale Fung

Natural Language Interfaces

Challenge:	Existing methods focus on improving in-domain performance, leaving open the question of how they can generalize to out-of-domain and unseen RC tasks.
Approach:	They propose a multi-task learning framework that learns the shared representation across different tasks and builds on a large pre-trained language model and fine-tuned on multiple RC datasets.
Outcome:	The proposed framework improves the BERT-Large baseline by 8.39 and 7.22 respectively.

EMCompress: Video-LLMs with Endomorphic Multimodal Compression (2026.findings-acl)

Copied to clipboard

Zheyu Fan, Jiateng Liu, Yuji Zhang, Zihan Wang, Yi R. Fung, Manling Li, Heng Ji

Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses (2026.acl-long)

Challenge:	Static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether.
Approach:	They propose a novel task that compresses multimodal input while preserving answer invariance across reasonable downstream models.
Outcome:	The proposed task surpasses prior methods by 0.40 F-1 with competitive query rewriting.

Copied to clipboard

Chongyuan Dai, Yaling Shen, Zihan Gao, Jia Li, Yishun Jiang, Yaxiong Wang, Liu Liu, Zongyuan Ge, Jinpeng Hu

Sentiment Analysis

Challenge:	Culture is a fundamental determinant of human affective processing and affective perceptions are often limited by declarative knowledge or established societal customs.
Approach:	They propose a multimodal benchmark that leverages LLM-generated provisional labels to isolate cross-cultural emotional distinctions.
Outcome:	The proposed benchmark captures cross-cultural emotional distinctions and derives reliable ground-truth annotations through human evaluation.

Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)

Copied to clipboard

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Exploiting Sentiment and Common Sense for Zero-shot Stance Detection (2022.coling-1)

Challenge:	Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature.
Approach:	They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization.
Outcome:	The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher.

Copied to clipboard

Yun Luo, Zihan Liu, Yuefeng Shi, Stan Z. Li, Yue Zhang

Sentiment Analysis

Challenge:	Existing stance detection models use sentiment and commonsense knowledge to classify stance toward documents and topics . obtaining rich annotated data in stance detector is time-consuming and laborintensive .
Approach:	They propose to use sentiment and commonsense knowledge to boost transferability of stance detection model by using sentiment and similar knowledge.
Outcome:	The proposed model outperforms the state-of-the-art methods on the zero-shot and few-shot benchmark datasets.

MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles (2025.findings-acl)

Copied to clipboard

Zihan Wang, Xiaocui Yang, YongKang Liu, Shi Feng, Daling Wang, Yifei Zhang

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models (2025.acl-long)

Challenge:	Existing research focuses solely on text, leaving a gap with practical applications.
Approach:	They propose to synthesize a multimodal conversational recommendation dataset using multimodal large language models to automatically synthesized data from 7,000 conversations in the Clothing domain.
Outcome:	The proposed dataset contains 83,148 utterances from 7,000 conversations centered around the Clothing domain.

Copied to clipboard

Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin

Programming Languages in NLP

Challenge:	Existing Mixture-of-Experts training frameworks use a micro-batch to calculate LBL . micro-batches are restricted to a single sequence, preventing expert specialization .
Approach:	They propose to use a global-batch to loosen the load balance constraint for MoEs models . they propose to synchronize fi across micro-batches and then use it to calculate the LBL .
Outcome:	The proposed global-batch LBL improves the domain specialization of experts . the micro-battery LBL is almost at the sequence level, and the router is pushed to distribute the token evenly .

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Copied to clipboard

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong

Numerical Reasoning

Challenge:	Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach:	They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome:	The proposed pipeline outperforms existing LLMs that could be two times larger.

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun

DualGuard: A Parameter Space Transformation Approach for Bidirectional Defense in Split-Based LLM Fine-Tuning (2025.acl-long)

Challenge:	Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach:	They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome:	The proposed framework improves performance of commercial and open-source models.

Copied to clipboard

Zihan Liu, Yizhen Wang, Rui Wang, Sai Wu

Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer (2021.emnlp-main)

Challenge:	Existing defense methods for large language model fine-tuning (LLM-FT) sacrifice task-specific performance under privacy constraints.
Approach:	They propose a bidirectional defense mechanism that uses a local warm-up parameter transformation to alter client-side model parameters before training.
Outcome:	The proposed defense mechanism outperforms current defense methods while maintaining task performance.

Copied to clipboard

Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang

Information Retrieval

Challenge:	Comparative Preference Classification (CPC) is a natural language processing task that predicts whether a preference comparison exists between two entities in a given sentence .
Approach:	They propose a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer.
Outcome:	Experiments on the CompSent-19 dataset present a significant improvement on the F1 scores over the best existing CPC approaches.

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization (2026.acl-long)

Copied to clipboard

Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

From Script to Stage: Automating Experimental Design for Social Simulations with LLMs (2026.findings-acl)

Challenge:	Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations.
Approach:	They analyze the current LLM learning paradigms to tackle four critical evaluation dimensions that have emerged as critical dimensions in recent studies.
Outcome:	The proposed models are able to interact with chemical spaces through natural language and symbolic notations, and have emerging extensions to incorporate multi-modal inputs.

Copied to clipboard

Yuwei Guo, Zihan Zhao, Xiaowei Liu, Xiangning Yu, Qun Ma, Deyu Zhou, Xiao Xue

Challenge:	Xu et al., 2024): multi-agent simulations based on large language models are a new paradigm for social science research . traditional experimental design relies on interdisciplinary expertise and technical barriers . Xiaoping and Xin eli argue that LLM-driven agents are unreliable for rigorous experimental design due to hallucinations and limited verifiability.
Approach:	They propose a framework for multi-agent experiment design based on script generation . Script Composition, Script Finalization, and Actor Generation are the core phases of the framework .
Outcome:	The proposed framework lowers the barrier for social science experimental design and provides scientifically grounded decision support for policy-making.

Multimodal End-to-End Sparse Model for Emotion Recognition (2021.naacl-main)

Copied to clipboard

Wenliang Dai, Samuel Cahyawijaya, Zihan Liu, Pascale Fung

Sentiment Analysis

Challenge:	Existing work in emotion recognition uses a two-phase pipeline, but the extracted features are fixed and cannot be fine-tuned on different tasks.
Approach:	They propose a two-phase pipeline for emotion recognition and personality recognition . they propose restructured datasets to enable fully end-to-end training .
Outcome:	The proposed model outperforms the current state-of-the-art models on emotion recognition and personality recognition tasks with half less computation in the feature extraction part.

Mere Contrastive Learning for Cross-Domain Sentiment Analysis (2022.coling-1)

Copied to clipboard

Yun Luo, Fang Guo, Zihan Liu, Yue Zhang

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (2020.acl-main)

Challenge:	Existing approaches to cross-domain sentiment analysis are labor-intensive and time-consuming.
Approach:	They propose a modified contrastive objective with in-batch negative samples to allow sentence representations from the same class to be pushed closer while those from the different classes become further apart in the latent space.
Outcome:	The proposed model can achieve state-of-the-art in cross-domain and multi-domain sentiment analysis tasks while transferring knowledge learned in the source domain to the target domain.

Copied to clipboard

Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung

Semantic Parsing

Challenge:	Existing approaches to slot filling are expensive and time-consuming.
Approach:	They propose a Coarse-to-fine approach for cross-domain slot filling . they propose utterance templates to regularize the representation of utterrances .
Outcome:	The proposed model outperforms state-of-the-art approaches in slot filling . it can be applied to the cross-domain named entity recognition task .

Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)

Copied to clipboard

Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang

Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition (D19-1)

Challenge:	Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations.
Approach:	They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function.
Outcome:	The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%.

Copied to clipboard

Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu, Pascale Fung

Representation Learning

Challenge:	Existing work on name-switching focuses on word-level aspects but neglects subword-level characteristics shared across languages.
Approach:	They propose hierarchical meta-Embeddings that combine word-level and subword-level embeddings to create language-agnostic lexical representations.
Outcome:	The proposed model achieves state-of-the-art in English-Spanish code-switching scenarios.

Meta-Transfer Learning for Code-Switched Speech Recognition (2020.acl-main)

Copied to clipboard

Genta Indra Winata, Samuel Cahyawijaya, Zhaojiang Lin, Zihan Liu, Peng Xu, Pascale Fung

ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation (2022.lrec-1)

Challenge:	Increasing number of people in the world today speak a mixed-language as a result of being multilingual.
Approach:	They propose a method to transfer learn on a code-switched speech recognition system by extracting information from high-resource monolingual datasets.
Outcome:	The proposed model outperforms baselines on speech recognition and language modeling tasks and is faster to converge.

Copied to clipboard

Holy Lovenia, Samuel Cahyawijaya, Genta Winata, Peng Xu, Yan Xu, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram Shi, Pascale Fung

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Code-switching is a speech phenomenon occurring when a speaker switches language during a conversation.
Approach:	They propose to collect Mandarin Chinese-English code-switching corpus from read speech rather than spontaneous speech to address this phenomenon.
Outcome:	ASCEND consists of 10.62 hours of clean speech, collected from 23 bilingual speakers of Chinese and English.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Information Retrieval

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling (2025.findings-acl)

Copied to clipboard

Zihan Liu, Yang Chen, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

Reasoning

Challenge:	In this paper, we introduce a suite of math models that excel in solving complex math problems.
Approach:	They propose a supervised fine-tuning process that achieves competitive performance across general domains, followed by targeted fine- tuning for the math domain using a carefully curated set of prompts and synthetically generated responses.
Outcome:	The proposed model outperforms Qwen2.5-Math-72B-Instruct, GPT-4o and Claude-3.5 Sonnet in the math domain.

CrossWeigh: Training Named Entity Tagger from Imperfect Annotations (D19-1)

Copied to clipboard

Zihan Wang, Jingbo Shang, Liyuan Liu, Lihao Lu, Jiacheng Liu, Jiawei Han

Information Extraction & Text Mining

Challenge:	Named entity recognition (NER) models can identify labels in 5.38% of test sentences . a framework to handle label mistakes during NER model training is proposed .
Approach:	They propose a framework to manually correct label mistakes in named entity recognition (NER) they aim to improve the accuracy of models by re-evaluating popular models on corrected test sets .
Outcome:	The proposed framework can detect label mistakes in 5.38% of test sentences . the proposed framework improves on three datasets with a high-performance model .

The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models (2026.findings-acl)

Copied to clipboard

Ruixing Zhang, Zihan Liu, Leilei Sun, Tongyu Zhu, Weifeng Lv

CodeContests+: High-Quality Test Case Generation for Competitive Programming (2025.findings-emnlp)

Challenge:	AGL1K is the first audio geo-localization benchmark for audio language models (ALMs) it is based on a crowd-sourced platform and is available in 72 countries and territories.
Approach:	They propose a benchmark for audio geo-localization that quantifies the informativeness of each recording and a metric that quantizes the information of each audio clip.
Outcome:	The proposed benchmarks cover 72 countries and territories and can be used to improve audio geo-localization.

Copied to clipboard

Zihan Wang, Siyao Liu, Yang Sun, Ming Ding, Hongyan Li

SUT: Active Defects Probing for Transcompiler Models (2023.emnlp-main)

Challenge:	Competitive programming has become a key task for training and evaluating large language models . but test cases of competitive programming problems are often difficult to obtain .
Approach:	They propose an LLM-based agent system that creates high-quality test cases for competitive programming problems.
Outcome:	The proposed system improves code tests on a CodeContests dataset with pass/fail labels.

Copied to clipboard

Mengnan Qi, Yufan Huang, Maoquan Wang, Yongqiang Yao, Zihan Liu, Bin Gu, Colin Clement, Neel Sundaresan

Machine Translation

Challenge:	Existing datasets are often criticized for their lack of granularity, which can mask deficiencies in basic syntactic elements that humans care about.
Approach:	They propose a new program translation metrics that address basic syntax errors . they propose BLUE, CodeBLUE and computation accuracy metrics which address these errors based on a highly interpretable evaluation harness.
Outcome:	The proposed model passes the unit tests with a 26.15% pass rate compared to previous models .

Identifying Collective Intelligence Factor in LLM Agent Groups for Generalizable Multi-Agent System Design (2026.findings-acl)

Copied to clipboard

Zhilun Zhou, Zihan Liu, Jiahe Liu, Yihan Wang, Qingyu Shao, Fengli Xu, Depeng Jin, Yong Li

Challenge:	Prior studies have focused on designing customized MAS for specific tasks . a critical research question remains: do LLM agent groups exhibit a form of "general intelligence"
Approach:	They find a Collective Intelligence factor in human groups that captures their general capability.
Outcome:	The proposed model predicts the ACI factor based on the features of LLM agent groups and can improve generalization abilities.

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models (2026.findings-acl)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

Challenge:	Long-context capabilities are essential for document and video understanding, in-contact learning, and inference-time scaling.
Approach:	They propose an efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens.
Outcome:	The proposed model extends the context window while maintaining short context capabilities while maintaining the performance of the existing model.

Copied to clipboard

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro

Multi-Stage Prompting for Knowledgeable Dialogue Generation (2022.findings-acl)

Challenge:	a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy.
Approach:	They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition .
Outcome:	The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks.

Copied to clipboard

Zihan Liu, Mostofa Patwary, Ryan Prenger, Shrimai Prabhumoye, Wei Ping, Mohammad Shoeybi, Bryan Catanzaro

Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking (2022.acl-long)

Challenge:	Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model and large-scale knowledge bases.
Approach:	They propose a multi-stage prompting approach to generate knowledgeable responses from a single pretrained LM.
Outcome:	The proposed model outperforms the state-of-the-art retrieval-based model in terms of knowledge relevance and correctness by 5.8% and 5%, respectively.

Copied to clipboard

Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang, Yixuan Liu

RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding (2023.findings-acl)

Challenge:	Experimental results show that task-oriented dialogue systems have attracted growing attention and achieved substantial progress.
Approach:	They propose a method that dynamically selects relevant dialogue contents for each slot . they retrieve turn-level utterances and evaluate their relevance to the slot from three perspectives .
Outcome:	The proposed method achieves state-of-the-art performance on MultiWOZ 2.1 and MultiWOz 2.2 and superior performance on multiple mainstream benchmark datasets.

Copied to clipboard

Ziwei Ji, Zihan Liu, Nayeon Lee, Tiezheng Yu, Bryan Wilie, Min Zeng, Pascale Fung

Structured Data in NLP

Challenge:	Existing knowledge-grounded dialogue systems generate accurate and informative responses, but they are prone to hallucination problems.
Approach:	They propose a method to generate hallucinated responses using knowledge graphs . they propose local knowledge grounding to combine textual embeddings with corresponding KG embeddments . a global knowledge ground technique is also proposed to equip RHO with multi-hop reasoning abilities .
Outcome:	The proposed approach outperforms state-of-the-art methods on automatic and human evaluation by a large margin.

Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training (2023.eacl-main)

Copied to clipboard

Wenliang Dai, Zihan Liu, Ziwei Ji, Dan Su, Pascale Fung

Calibrating LLM-Based Evaluator (2024.lrec-main)

Challenge:	Large-scale vision-language pre-trained (VLP) models generate unfaithful or nonsensical texts given the source input, which is called hallucination.
Approach:	They propose a VLP loss-based model to mitigate object hallucination by decoupling VLP objectives and a token-level image-text alignment.
Outcome:	The proposed model reduces object hallucination by 17.4% on two benchmarks.

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Existing models for large language models lack the ability to calibrate their outputs towards human preference.
Approach:	They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference.
Outcome:	The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets.

Copied to clipboard

Zihan Liu, Genta Indra Winata, Pascale Fung

Multilinguality

Challenge:	a lack of data in low-resource languages has limited the performance of a multilingual pre-trained model.
Approach:	They propose a continuous pre-training framework to adapt mBART to unseen languages . they construct noisy mixed-language text from the monolingual corpus of the target language .
Outcome:	The proposed framework improves finetuning performance on low-resource translation pairs . the proposed framework also improves on translation pairs where both languages are seen .

EviReport: From Reasoned Outlines to Evidence Tracked Long-Form Reports (2026.findings-acl)

Copied to clipboard

Zihan Liu, Jianhui li, Zexin Wang, Fei Sun, Jingjing LI, Zheyuan Li, Ke Xiang, Hang Cui, Houhua Gong, Changhua Pei, Gaogang Xie

Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition (2020.aacl-main)

Challenge:	Evidence-intensive reports often produce fluent but under-supported drafts . eviReport is an evidence-grounded workflow for automated long-form report generation .
Approach:	They propose an evidence-tracked workflow that organizes corpus evidence into compact, traceable units and retrieves query-relevant subgraphs into retrieval-ready packages.
Outcome:	The proposed workflow outperforms baselines in factual coverage, factual accuracy and visual evidence integration.

Copied to clipboard

Wenliang Dai, Zihan Liu, Tiezheng Yu, Pascale Fung

Cross-lingual Spoken Language Understanding with Regularized Representation Alignment (2020.emnlp-main)

Challenge:	despite recent advances in multimodal emotion recognition, two problems still exist: sub-optimal performance and low-resource emotions.
Approach:	They propose a modality-transferable model with emotion embeddings to solve these problems . they use pre-trained word embedders to represent emotion categories for textual data .
Outcome:	The proposed model outperforms baselines in zero-shot and few-shot scenarios for unseen emotions.

Copied to clipboard

Zihan Liu, Genta Indra Winata, Peng Xu, Zhaojiang Lin, Pascale Fung

Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition (2024.lrec-main)

Challenge:	despite promising results, current cross-lingual models suffer from imperfect cross-linguistic representation alignments between the source and target languages, which makes the performance sub-optimal.
Approach:	They propose a regularization approach to align word-level and sentence-level representations across languages without external resources.
Outcome:	The proposed model outperforms state-of-the-art models in few-shot and zero-shot scenarios and achieves comparable performance to supervised training with all training data.

Copied to clipboard

Zihao Zheng, Zihan Zhang, Zexin Wang, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin

iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation (2025.acl-demo)

Challenge:	Existing research on multi-modal Named Entity Recognition (MNER) does not integrate all multi-modal representations to provide rich contextual information to improve NER.
Approach:	They propose an iterative reasoning framework that integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate" . they propose to use hierarchically connected fusion layers to prioritize transitions from "easy-to-hard" and "coarse-to fine"
Outcome:	The proposed framework integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate".

Copied to clipboard

Zheyong Xie, Shaosheng Cao, Zuozhu Liu, Zheyu Ye, Zihan Niu, Chonggang Lu, Tong Xu, Enhong Chen, Zhe Xu, Yao Hu, Wei Lu

Answer is All You Need: Instruction-following Text Embedding via Answering the Question (2024.acl-long)

Challenge:	Existing approaches to role-playing emotional companion products lack sustained personalization and contextual adaptability, limiting their effectiveness in real-world settings.
Approach:	They propose a virtual pet agent that can enhance user engagement through rich, dynamic pet behaviors and interactions tailored to individual preferences.
Outcome:	The proposed system has been deployed in a real-world, non-commercial product for 200 days and has demonstrated its effectiveness in practical applications.

Copied to clipboard

Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang

DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	Existing methods for encoding instruction information fail to be sensitive to clearer criteria like “evaluate similarity based on emotion” . instead, we propose a different approach, which treats the instruction as a “question” about the input text and encodes the expected answers to obtain the representation accordingly.
Approach:	They propose a text embedder that captures characteristics of texts specified by user instructions clarifying the similarity criterion.
Outcome:	The proposed model improves instruction-following capabilities when applied to large language models and encoder-based LMs.

Copied to clipboard

Chunkit Chan, Xin Liu, Jiayang Cheng, Zihan Li, Yangqiu Song, Ginny Wong, Simon See

LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Challenge:	Existing works on implicit discourse relation recognition focus on syntax features and lack of connectives.
Approach:	They propose a prompt-based path prediction method that integrates the interactive information and intrinsic senses among the hierarchy in IDRR.
Outcome:	The proposed method shows significant improvement against competitive baselines.

Copied to clipboard

Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun