Papers by Xiaodan Zhu

Exploring Decomposition for Table-based Fact Verification (2021.findings-emnlp)

Challenge:	Existing methods for mitigating bias in language models are expensive and time-consuming . comparative studies have not evaluated their respective advantages and disadvantages .
Approach:	They propose to use Partitioned Contrastive Gradient Unlearning and Negation via Task Vector to reduce social biases in open-source language models.
Outcome:	The proposed methods outperform PCGU and DPO in debiasing models . the proposed methods can be easily tuned to balance the trade-off between bias reduction and generation quality .

Copied to clipboard

Xiaoyu Yang, Xiaodan Zhu

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning (2021.findings-emnlp)

Challenge:	Existing research focuses on fact verification based on unstructured text, but structured data is becoming more prevalent.
Approach:	They propose to decompose complex statements into simpler subproblems to improve table-based verification by a weakly supervised parser.
Outcome:	The proposed method achieves state-of-the-art accuracy on the TabFact benchmark.

Copied to clipboard

Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu

Prototype-Based Interpretability for Legal Citation Prediction (2023.findings-acl)

Challenge:	Existing approaches fail to generalize well to concepts that are not observed during training.
Approach:	They propose a framework that revolves around probing several similar image caption training instances and performing analogical reasoning over relevant entities in retrieved prototypes.
Outcome:	The proposed framework improves on the widely used image captioning benchmarks and on composition-related evaluation metrics.

Copied to clipboard

Chu Fei Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Explainability & Interpretability in NLP

Challenge:	citation prediction is a key problem in high-stakes decision making areas such as law . experts often require interpretability for automatic systems to be utilized in practical settings .
Approach:	They propose to use legal citation prediction to solve a problem with legal experts' feedback . they propose to add a prototype architecture to add interpretability while adhering to legal parameters .
Outcome:	The proposed model performs well while adhering to decision parameters used by lawyers.

Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration (2022.acl-long)

Copied to clipboard

Xiwen Liang, Fengda Zhu, Li Lingling, Hang Xu, Xiaodan Liang

Exploring End-to-End Differentiable Natural Logic Modeling (2020.coling-main)

Challenge:	Existing methods of fine-tuning vision-language navigation models require extra human-labeled data and lack self-exploration capabilities in environments.
Approach:	They propose a method that can self-explore environments without human labeling . they use a large-scale cross-modal pretrained model to build an in-domain dataset .
Outcome:	The proposed model can self-explore environments without human labeling without human supervision and generates structured instructions without human intervention.

Copied to clipboard

Yufei Feng, Zi’ou Zheng, Quan Liu, Michael Greenspan, Xiaodan Zhu

Improving Image Captioning with Better Use of Caption (2020.acl-main)

Challenge:	Existing approaches to integrate natural logic with neural networks are brittle and prone to fail in the presence of noise and uncertainty.
Approach:	They propose to integrate natural logic with neural networks to create differentiable models that integrate natural reasoning with subsymbolic vector representations and neural components.
Outcome:	The proposed model can model monotonicity-based reasoning, compared to baseline models without inductive bias.

Copied to clipboard

Zhan Shi, Xu Zhou, Xipeng Qiu, Xiaodan Zhu

Robust Utility-Preserving Text Anonymization Based on Large Language Models (2025.acl-long)

Challenge:	Existing approaches to image captioning focus on visual attention, but many do not.
Approach:	They propose a framework that explores semantics available in captions and leverages that to enhance both image representation and caption generation.
Outcome:	The proposed framework outperforms baselines on the MSCOCO dataset and is state-of-the-art under a wide range of evaluation metrics.

Copied to clipboard

Tianyu Yang, Xiaodan Zhu, Iryna Gurevych

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions (2023.findings-acl)

Challenge:	Existing techniques face challenges of re-identification ability of large language models . anonymizing text that contains sensitive information is crucial for a wide range of applications .
Approach:	They propose a framework that integrates three key LLM components to perform anonymization.
Outcome:	The proposed model outperforms baselines while maintaining greater data utility in downstream tasks.

Copied to clipboard

Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic (2023.acl-long)

Challenge:	Existing benchmarks focus on a single reasoning type and ask human annotators to write candidate statements related to the particular type of commonsense.
Approach:	They propose a new commonsense reasoning dataset based on human’s Interactive Fiction (IF) gameplaywalkthroughs.
Outcome:	The proposed dataset is challenging to previous machine reading models and large language models with a significant 20%performance gap compared to human experts.

Copied to clipboard

Zi’ou Zheng, Xiaodan Zhu

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Challenge:	Despite the recent advances in distributed representation and neural networks, it remains an open question whether the models perform real reasoning to reach their conclusions or rely on spurious correlations.
Approach:	They propose to use logic formalism to perform systematic attacks centring around natural logic to generate better adversarial examples with fewer visits to the victim models.
Outcome:	The proposed framework generates better adversarial examples with fewer visits to the victim models.

Copied to clipboard

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Text Generation

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models (2025.findings-acl)

Copied to clipboard

Marcus Tantakoun, Christian Muise, Xiaodan Zhu

Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Challenge:	Large Language Models excel in various natural language tasks but struggle with long-horizon planning problems requiring structured reasoning.
Approach:	They propose to integrate large language models into AP and NLP planning frameworks by reviewing current research and identifying critical challenges and future directions.
Outcome:	The proposed frameworks are used to support reliable off-the-shelf AP planners.

Copied to clipboard

Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021.acl-short)

Challenge:	Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach:	They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome:	The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.

Copied to clipboard

Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu

Enhancing Descriptive Image Captioning with Natural Language Inference (2021.acl-short)

Challenge:	Existing dialog state tracking models neglect rich structural information in a dataset.
Approach:	They propose to use curriculum learning to leverage dialog state tracking data . they propose a model-agnostic framework that pre-trains a DST model with schema information .
Outcome:	The proposed framework improves performance over a transformer-based and RNN-based model on WOZ2.0 and MultiWOZ2.1.

Copied to clipboard

Zhan Shi, Hui Liu, Xiaodan Zhu

Text Generation

Challenge:	Existing captioning models tend to generate generic captions, but generating descriptive captions is important.
Approach:	They propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference.
Outcome:	The proposed method outperforms baseline models on MSCOCO metrics on descriptiveness and descriptiveness.

SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration (2024.emnlp-industry)

Copied to clipboard

Yuanhao Shen, Xiaodan Zhu, Lei Chen

DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have a profound impact on a wide range of applications.
Approach:	They propose a framework to mitigate the tool-abuse behavior of Large Language Models and propose SMARTCAL to mitigate this issue.
Outcome:	The proposed framework improves the performance of LLMs on three datasets with two mainstream tool-use frameworks and shows an 8.6% increase in QA performance and 21.6 percent lower expected calibration error (ECE) than existing methods.

Copied to clipboard

Haishuo Fang, Xiaodan Zhu, Iryna Gurevych

Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks (2023.emnlp-industry)

Challenge:	Existing approaches to answer questions over Knowledge Graphs (KGQA) are not available for KGQA.
Approach:	They propose a framework to improve the neural-symbolic reasoning capabilities of language agents powered by Large Language Models (LLMs) they show that DARA can be efficiently trained with a small number of high-quality reasoning trajectories.
Outcome:	The proposed framework outperforms in-context learning-based agents with GPT-4 and alternative fine-tuned agents across different benchmarks.

Copied to clipboard

Xianzhi Li, Samuel Chan, Xiaodan Zhu, Yulong Pei, Zhiqiang Ma, Xiaomo Liu, Sameena Shah

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation (2024.findings-emnlp)

Challenge:	Recent large language models such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models . however, their applicability and effectiveness in specific domains like finance needs a better understanding .
Approach:	They conduct empirical studies to compare the performance of ChatGPT and GPT-4 on financial text analytical problems using eight benchmark datasets from five categories of tasks.
Outcome:	The proposed models outperform the state-of-the-art models on a wide range of financial text analytical tasks.

Copied to clipboard

Xianzhi Li, Ran Zmigrod, Zhiqiang Ma, Xiaomo Liu, Xiaodan Zhu

CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment (2026.acl-long)

Challenge:	Language models can memorize detailed information and patterns, but raise privacy concerns . ANADP reduces the performance gap between regular and DP fine-tuning while maintaining the privacy constraints.
Approach:	They propose an algorithm that allocates additive noise based on the importance of model parameters to reduce the performance gap between regular fine-tuning and traditional DP fine- tuning.
Outcome:	The proposed algorithm narrows the performance gap between regular fine-tuning and traditional DP fine- tuning while maintaining privacy constraints.

Copied to clipboard

Radin Shayanfar, Chu Fei Luo, Rohan V Bhambhoria, Samuel Dahan, Xiaodan Zhu

Natural Language Interfaces

Challenge:	Recent schema-based TOD frameworks improve generalization by decoupling task logic from language understanding, but their reliance on neural or generative models obscures how task schemas influence behaviour and hence impair interpretability.
Approach:	They propose a framework that converts a predefined task schema to a structured heterogeneous graph and then to popular programmatic LLM guardrailing code, such as NVIDIA’s Colang.
Outcome:	The proposed framework achieves state-of-the-art performance on the widely used benchmark datasets while providing inherent interpretability in the design.

Deep Learning for Natural Language Inference (N19-5)

Copied to clipboard

Samuel Bowman, Xiaodan Zhu

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots (2020.findings-emnlp)

Challenge:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning for language understanding and reasoning.
Approach:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development and cutting- edge deep learning models.
Outcome:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning model for language understanding and reasoning.

Copied to clipboard

Jia-Chen Gu, Zhenhua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu

Natural Language Interfaces

Challenge:	Experimental results show that FIRE outperforms previous methods for building knowledge-grounded retrieval-based chatbots . a method called Filtering before iteratively referring is used to ground a conversation on background knowledge .
Approach:	They propose a method for grounding conversation on background knowledge . they use context filter and knowledge filter to make context and knowledge aware . experimental results show that FIRE outperforms previous methods .
Outcome:	The proposed method outperforms previous methods on two datasets.

WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge (2021.emnlp-main)

Copied to clipboard

Weinan He, Canming Huang, Yongmei Liu, Xiaodan Zhu

Developing Prefix-Tuning Models for Hierarchical Text Classification (2022.emnlp-industry)

Challenge:	Recent success of neural language models on the Winograd Schema Challenge has called for further investigation of commonsense reasoning ability of these models.
Approach:	They propose a logic-based framework that focuses on high-quality commonsense knowledge.
Outcome:	The proposed framework focuses on high-quality commonsense knowledge.

Copied to clipboard

Lei Chen, Houwei Chou, Xiaodan Zhu

Information Extraction & Text Mining

Challenge:	Hierarchical text classification (HTC) is a key task in many industrial applications. Pre-trained Language Models (PLMs) have become dominant for most natural language processing (NLP) tasks.
Approach:	They investigate how prefix tuning can improve hierarchical text classification . prefix-tuning model only needs less than 1% of parameters to achieve performance .
Outcome:	The proposed model can achieve comparable performance to regular full fine-tuning.

Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning (2021.acl-long)

Copied to clipboard

Pan Lu, Ran Gong, Shibiao Jiang, Liang Qiu, Siyuan Huang, Xiaodan Liang, Song-Chun Zhu

Induction Networks for Few-Shot Text Classification (D19-1)

Challenge:	Existing methods for solving geometric problems are either small in scale or not publicly available.
Approach:	They propose a large-scale benchmark for geometric problem solving using formal language and symbolic reasoning.
Outcome:	The proposed approach parses geometry problems into formal language and performs symbolic reasoning step by step.

Copied to clipboard

Ruiying Geng, Binhua Li, Yongbin Li, Xiaodan Zhu, Ping Jian, Jian Sun

A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification (2023.acl-short)

Challenge:	Recent studies have used meta-learning to simulate the few-shot task . however, this sample-wise comparison may be severely disturbed by the various expressions in the same class.
Approach:	They propose a meta-learning-based induction network to learn a generalized class-wise representation of each class in a support set.
Outcome:	The proposed model outperforms existing state-of-the-art models on a sentiment and dialogue intent datasets.

Copied to clipboard

Rohan Bhambhoria, Lei Chen, Xiaodan Zhu

Dynamic Memory Induction Networks for Few-Shot Text Classification (2020.acl-main)

Challenge:	Large language models have been able to perform well on benchmarks, but they are often not able address real-world challenges.
Approach:	They propose to refactor hierarchical tasks into a more indicative long-tail prediction task.
Outcome:	The proposed method does not require parameter updates and achieves strong performance across multiple datasets.

Copied to clipboard

Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

Information Extraction & Text Mining

Challenge:	Recent studies have shown that models can benefit from query-aware methods for few-shot text classification.
Approach:	They propose a dynamic memory-based network for few-short text classification that uses static memory to adapt to unseen classes.
Outcome:	The proposed model improves on the miniRCV1 and ODIC datasets by 24% . Detailed analysis is performed to show how the proposed network achieves the new performance.

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data (2026.eacl-long)

Copied to clipboard

Paul Quinlan, Qingguo Li, Xiaodan Zhu

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning (2022.emnlp-main)

Challenge:	Large language models are being rapidly applied across many fields such as healthcare, finance, transportation, and energy.
Approach:	They propose a large language model framework that integrates time-series tokens into LLMs’ vocabulary, enhancing its reasoning ability over time- and textual data.
Outcome:	The proposed framework enhances reasoning ability over time-series and textual data without compromising core natural language capabilities.

Copied to clipboard

Yi Zhu, Zhaoqing Zhu, Bingqian Lin, Xiaodan Liang, Feng Zhao, Jianzhuang Liu

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models (2024.acl-long)

Challenge:	Existing visual relationship detection models only use numeric ids of relation labels for training, but ignore semantic correlation between labels.
Approach:	They propose a visual Relationship prediction framework that transfers natural language knowledge from Contrastive Language-Image Pre-training models to enhance the relationship prediction.
Outcome:	The proposed framework improves visual relationship prediction by matching semantic correlations with relation triplets.

Copied to clipboard

Md Imbesat Rizvi, Xiaodan Zhu, Iryna Gurevych

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback (2025.findings-emnlp)

Challenge:	Existing large language models (LLMs) do not perform well on the datasets.
Approach:	They propose to use a Spatial Reasoning Characterization framework and a spatial reasoning path framework to study spatial reasoning.
Outcome:	The proposed framework and datasets outperform state-of-the-art models in spatial reasoning.

Copied to clipboard

Chu Fei Luo, Samuel Dahan, Xiaodan Zhu

Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020.emnlp-main)

Challenge:	popular training paradigms for language models often assume there is one optimal answer for every query.
Approach:	They propose to enhance pluralistic alignment of language models using pluralistic decoding and model steering methods.
Outcome:	The proposed methods improve pluralistic alignment of language models in a low-resource setting . the proposed methods decrease false positives in several high-stakes tasks .

Copied to clipboard

Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen, Xiaodan Zhu

Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models (2024.emnlp-main)

Challenge:	Existing methods for fact verification based on structured data are challenging and require further study.
Approach:	They propose a program-enhanced verbalization and a graph attention network to integrate programs and execution into textual inference models.
Outcome:	The proposed framework achieves a new state-of-the-art accuracy on a benchmark dataset . it is compared with existing frameworks on symbolic and informal inference models .

Copied to clipboard

Zi’ou Zheng, Christopher Malon, Martin Min, Xiaodan Zhu

The State of the Art of Large Language Models on Chartered Financial Analyst Exams (2024.emnlp-industry)

Challenge:	Large language models (LLMs) are essential for performing complex multi-step reasoning tasks, such as multi-hop reasoning tasks.
Approach:	They propose to use large language models to derive structured intermediate proof steps to improve their performance by using examples.
Outcome:	The proposed models can derive correct proof steps with in-context learning.

Copied to clipboard

Mahmoud Mahfouz, Ethan Callanan, Mathieu Sibue, Antony Papadimitriou, Zhiqiang Ma, Xiaomo Liu, Xiaodan Zhu

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs (2025.acl-long)

Challenge:	Chartered Financial Analyst (CFA) program is widely recognized globally . study compares state-of-the-art large language models with open-source models . proprietary models pass levels I and II, but fail at level III due to essay questions .
Approach:	They benchmark five leading proprietary models and eight open-source models on mock CFA exams to provide an overview of their financial analysis capabilities.
Outcome:	The models on the mock CFA exams pass the highest scores, but fail at the lowest levels due to essay questions.

Copied to clipboard

Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych

Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy (2021.emnlp-main)

Challenge:	Existing approaches to generate multiple independent CoTs, combining them through ensembling or other post-hoc strategies, have been shown to be effective in boosting performance.
Approach:	They propose a method where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.
Outcome:	The proposed model can generate multiple chains of thought within a single inference step without external feedback.

Copied to clipboard

Dayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation (2024.findings-emnlp)

Challenge:	Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.
Approach:	They propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn.
Outcome:	The proposed model can predict the participant's emotion in the next upcoming turn without knowing the participant’s response yet.

Copied to clipboard

Chu Fei Luo, Radin Shayanfar, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Challenge:	Existing research has focused on the veracity of information, overlooking the legal implications and consequences of misinformation.
Approach:	They propose a task to detect misinformation using legal issues as a measure of societal ramifications.
Outcome:	The proposed task leverages definitions from a wide range of legal domains covering 4 broader legal topics and 11 fine-grained legal issues, including hate speech, election laws, and privacy regulations.

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

Legally Enforceable Hate Speech Detection for Public Forums (2023.findings-emnlp)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Chu Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs (2024.emnlp-main)

Challenge:	Existing work does not align systems with enforceable hate speech definitions, which can make outputs inconsistent with the goals of regulators.
Approach:	They propose a task for enforceable hate speech detection centred around legal definitions and an annotated dataset of violations by legal experts.
Outcome:	The proposed method can be used to detect hate speech in public forums on a large scale.

Copied to clipboard

Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych

Prefix Propagation: Parameter-Efficient Tuning for Long Sequences (2023.acl-short)

Challenge:	Recent prompting techniques have improved LLMs’ performance on various reasoning tasks, but there is little understanding of what triggers reasoning abilities in LLM in the inference stage.
Approach:	They propose a method that transforms a natural language problem into code and directly prompts the LLM using the generated code without resorting to external code execution.
Outcome:	The proposed method boosts multiple LLMs by 22.52 percentage points on GPT 3.5, 7.75 on Mixtral, and 16.78 on Mistral.

Copied to clipboard

Jonathan Li, Will Aitken, Rohan Bhambhoria, Xiaodan Zhu

Green & Sustainable NLP

Challenge:	Prefix-tuning prepends trainable tokens to sequences while freezing the rest of the model’s parameters.
Approach:	They propose a method that prefixes on previous hidden states to improve model performance.
Outcome:	The proposed architecture outperforms prefix-tuning on long-document tasks while using 50% fewer parameters.

Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment (2020.acl-main)

Copied to clipboard

Yinpei Dai, Hangyu Li, Chengguang Tang, Yongbin Li, Jian Sun, Xiaodan Zhu

Neural Natural Language Inference Models Enhanced with External Knowledge (P18-1)

Challenge:	Existing end-to-end dialog systems perform less effectively when data is scarce.
Approach:	They propose a Meta-Dialog System which combines meta-learning and human-machine collaboration to improve dialog learning by a new extended-bAbI dataset and a transformed MultiWOZ dataset.
Outcome:	The proposed system outperforms non-meta-learning baselines on a new extended-bAbI dataset and a transformed MultiWOZ dataset for low-resource goal-oriented dialog learning.

Copied to clipboard

Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, Si Wei

Unsupervised Conversation Disentanglement through Co-Training (2021.emnlp-main)

Challenge:	Existing datasets that allow for complex models to be trained are limited . if data is not available, can machines learn all knowledge needed to perform natural language inference?
Approach:	They propose to enrich neural natural language inference models with external knowledge . they propose to use this knowledge to build NLI models to leverage it .
Outcome:	The proposed models improve on the SNLI and MultiNLI datasets.

Copied to clipboard

Hui Liu, Zhan Shi, Xiaodan Zhu

Information Retrieval

Challenge:	Existing work on conversation disentanglement relies heavily on human annotations, which is expensive to obtain in practice.
Approach:	They propose to train a conversation disentanglement model without referencing human annotations . they use a message-pair classifier and a session classifier to retrieve local relations .
Outcome:	The proposed method achieves competitive performance compared to previous methods on a large movie dialogue dataset.

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning (2021.naacl-main)

Copied to clipboard

Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu

OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)

Challenge:	Existing zero-shot learning methods for multi-label text classification mostly learn a matching model between the feature space of text and the label space.
Approach:	They propose to use a graph encoder to incorporate label hierarchies to learn effective label representations on the zero-shot multi-label text classification problem.
Outcome:	The proposed approach outperforms previous non-pretrained methods on the zero-shot multi-label text classification task.

Copied to clipboard

Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu

Preemptive Detection and Correction of Misaligned Actions in LLM Agents (2025.emnlp-main)

Challenge:	Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model .
Approach:	They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias.
Outcome:	The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones.

Copied to clipboard

Haishuo Fang, Xiaodan Zhu, Iryna Gurevych

Challenge:	Large Language Models (LLMs) have revolutionized human-AI collaboration by enabling autonomous agents to execute complex, multi-step tasks.
Approach:	They propose a method that leverages the belief reasoning ability of LLMs to detect misaligned actions.
Outcome:	Experiments on three widely used tasks show that InferAct outperforms other methods on Marco-F1 and emnlp2025.

Enhancing Sentence Embedding with Generalized Pooling (C18-1)

Copied to clipboard

Qian Chen, Zhen-Hua Ling, Xiaodan Zhu

Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference (2022.tacl-1)

Challenge:	Existing methods for learning sentence embedding are limited, but still need to be improved.
Approach:	They propose a vector-based multi-head attention model that uses special cases of max pooling, mean pooling and scalar self-attention.
Outcome:	The proposed model improves on natural language inference, author profiling, and sentiment classification tasks.

Copied to clipboard

Yufei Feng, Xiaoyu Yang, Xiaodan Zhu, Michael Greenspan

Explainability & Interpretability in NLP

Challenge:	a neural network model for natural language inference (NLI) is proposed.
Approach:	They propose a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision that rewards specific reasoning paths through policy gradients.
Outcome:	The proposed model shows superior capability in monotonicity inference, generalization, and interpretability compared with previous models on the existing datasets.

Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots (D19-1)

Copied to clipboard

Jia-Chen Gu, Zhen-Hua Ling, Xiaodan Zhu, Quan Liu

Natural Language Interfaces

Challenge:	Existing models for personalized dialogues rank responses according to their semantic relevance with the given context.
Approach:	They propose a dually interactive matching network (DIM) for presenting personalities of dialogue agents in retrieval-based chatbots.
Outcome:	The proposed model outperforms the existing model by 14.5% and 27.7% on a PERSONA-CHAT dataset.

Detecting Speaker Personas from Conversational Texts (2021.emnlp-main)

Copied to clipboard

Jia-Chen Gu, Zhenhua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu