Papers by Min-Yen Kan

It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations (2020.acl-main)

Challenge:	Current methods for reasoning and predicting human opinions employ role-playing with personae but face two major issues: LLMs are sensitive to even a single irrelevant persona, skewing predictions by up to 30%; and LLM fail to reason strategically over personas.
Approach:	They propose a four-step solution modeling which and how to reason with personae, inspired by the Value–Belief–Norm theory.
Outcome:	The proposed model improves existing methods by up to 4% by fine-tuning them with COO's data.

Copied to clipboard

Samson Tan, Shafiq Joty, Min-Yen Kan, Richard Socher

Songs Across Borders: Singable and Controllable Neural Lyric Translation (2023.acl-long)

Challenge:	Existing work on societal bias in NLP focuses on race and gender . linguistic background is a unique attribute that has been largely ignored in the field .
Approach:	They examine linguistic background to craft plausible adversarial examples that expose biases in popular NLP models.
Outcome:	The proposed model improves robustness without sacrificing performance on clean data.

Copied to clipboard

Longshen Ou, Xichu Ma, Min-Yen Kan, Ye Wang

Machine Translation

Challenge:	Obtaining singable lyric translations can facilitate the globalization of the music publishing industry .
Approach:	They formalize lyric translation into a constrained translation problem and instantiate them to an English-Chinese system.
Outcome:	The proposed model achieves 99.85%, 99.00%, and 95.52% on length accuracy, rhyme accuracy, and word boundary recall.

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization (2024.findings-emnlp)

Copied to clipboard

Yuxi Xie, Guanzhen Li, Xiao Xu, Min-Yen Kan

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer (2022.acl-long)

Challenge:	Existing large vision-language models suffer from hallucination due to over-reliance on the Large Language Model (LLM) backbone.
Approach:	They propose a method to improve visual context learning by using a large-scale preference learning algorithm to improve hallucination.
Outcome:	The proposed method improves on human-annotated hallucination datasets.

Copied to clipboard

Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann, Soujanya Poria

Fact-Checking Complex Claims with Program-Guided Reasoning (2023.acl-long)

Challenge:	Automated transfer of text between domains does not maintain other attributes between the source and translated text.
Approach:	They propose a method for automatic transfer of text between domains that preserves semantic content but changes other attributes.
Outcome:	The proposed method retains lexical, syntactic and domain-specific constraints between domains for multiple benchmark datasets, including ones where more than one attribute change.

Copied to clipboard

Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

Programming Languages in NLP

Challenge:	Fact-checking real-world claims often requires collecting multiple pieces of evidence and complex multi-step reasoning.
Approach:	They propose a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions.
Outcome:	The proposed model outperforms seven baselines on two fact-checking datasets and has explicit output programs that benefit human debugging.

What Makes a Good Natural Language Prompt? (2025.acl-long)

Copied to clipboard

Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen, Kenji Kawaguchi, Nancy F. Chen, Shafiq Joty, Min-Yen Kan

What’s Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews (2026.acl-long)

Challenge:	Existing studies on prompt quality show imbalanced support across models and tasks, and research gaps.
Approach:	They propose a property- and human-centric framework for evaluating prompt quality . they propose comparing prompt quality to other factors such as adverbs and apverbs .
Outcome:	The proposed framework reveals imbalanced support across models and tasks and substantial research gaps.

Copied to clipboard

Fanxiao Li, Jiaying Wu, Tingchao Fu, Dayang Li, Herun Wan, Wei Zhou, Min-Yen Kan

CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations (2022.coling-1)

Challenge:	Existing efforts to detect factually incorrect content are omitted by creators who subtly reshape impressions by omitting crucial background context.
Approach:	They propose a multi-stage pipeline that simulates preview-based and context-based understanding and a OMGuard pipeline that combines interpretation-aware fine-tuning and rationale-guided misleading content correction.
Outcome:	The proposed framework lifts an 8B model’s detection accuracy to the level of a 235B LVLM while delivering stronger end-to-end correction.

Copied to clipboard

Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, See-Kiong Ng

Dialogue Systems & Conversational Agents

Challenge:	Document-grounded dialogs need smooth transitions between knowledge selected for generating responses.
Approach:	They propose a multi-document co-referential graph to capture inter- and intra-document relationships . they propose 'Coref-MDG' method to linearize static Coref-mDG into conversational sequence logic.
Outcome:	The proposed method outperforms the state-of-the-art by 9.5%, 7.4% and 8.2% on three public benchmarks.

Beyond Memorization: The Challenge of Random Memory Access in Language Models (2024.acl-long)

Copied to clipboard

Tongyao Zhu, Qian Liu, Liang Pang, Zhengbao Jiang, Min-Yen Kan, Min Lin

Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding (2020.emnlp-main)

Challenge:	Recent advances in Language Models (LMs) have shown their effectiveness in knowledge-intensive tasks.
Approach:	They investigate whether a generative language model is able to access its memory sequentially or randomly.
Outcome:	The proposed LMs are able to access memory sequentially or randomly.

Copied to clipboard

Samson Tan, Shafiq Joty, Lav Varshney, Min-Yen Kan

Predicting Helpful Posts in Open-Ended Discussion Forums: A Neural Architecture (N19-1)

Challenge:	Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.
Approach:	They propose a method to tokenize English text by reducing inflected words to their base forms before reinjecting the grammatical information as special symbols.
Outcome:	The proposed method defends against inflectional adversaries while maintaining performance on clean data.

Copied to clipboard

Kishaloy Halder, Min-Yen Kan, Kazunari Sugiyama

Challenge:	Unlike Community Question Answering, where questions are mostly factoid based, forum threads are often open-ended and contain repetitive or irrelevant posts.
Approach:	They propose a recurrent neural network-based architecture to model the relevance of a post regarding the original post starting the thread and the novelty it brings to the discussion.
Outcome:	The proposed model outperforms the state-of-the-art models for text classification on different types of online forum datasets.

UDAPTER - Efficient Domain Adaptation Using Adapters (2023.eacl-main)

Copied to clipboard

Bhavitvya Malik, Abhinav Ramesh Kashyap, Min-Yen Kan, Soujanya Poria

Sentiment Aware Neural Machine Translation (D19-52)

Challenge:	Using adapters, unsupervised domain adaptation (UDA) is more parameter efficient and requires large-scale data to be effective.
Approach:	They propose to add small bottleneck layers to each layer of a pre-trained language model to make it more parameter efficient by adding adapters.
Outcome:	The proposed methods outperform unsupervised domain adaptation methods such as DANN and DSN in natural language inference and sentiment classification tasks.

Copied to clipboard

Chenglei Si, Kui Wu, Ai Ti Aw, Min-Yen Kan

Text Generation

Challenge:	Sentiment ambiguous lexicons are used when context is absent in translations . most systems aim to produce one correct translation for a given source sentence .
Approach:	They propose a neural machine translation method that preserves sentiment in two sentiment scenarios and a method that embeds sentiment into a sentence.
Outcome:	The proposed method outperforms a baseline with sentiment-aware translations in both the BLEU score and translation accuracy.

DataTales: A Benchmark for Real-World Intelligent Data Narration (2024.emnlp-main)

Copied to clipboard

Yajing Yang, Qian Liu, Min-Yen Kan

Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent? (2025.findings-emnlp)

Challenge:	Existing benchmarks fail to capture the requisite analytical complexity for practical applications.
Approach:	They propose a benchmark to assess the proficiency of language models in data narration.
Outcome:	The proposed model combines financial reports with market data to demonstrate proficiency in data narration.

Copied to clipboard

Xi Ai, Mahardika Krisna Ihsani, Min-Yen Kan

Multilinguality

Challenge:	Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain factuality of model knowledge across languages, and preserve parity of language model performance.
Approach:	They examine pretrained and tuned models with code-mixed coreferential statements that convey identical knowledge across languages.
Outcome:	The proposed model shows different levels of consistency in multilingual models, subject to language families, linguistic factors, scripts, and bottlenecks on a particular layer.

ComicVQA: A Benchmark for Visual Reasoning in Multimodal LLMs (2026.findings-acl)

Copied to clipboard

Esther Gan, Hannah Brown, David Herel, Kenji Kawaguchi, Min-Yen Kan, Michael Qizhe Shieh

QACheck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking (2023.emnlp-demo)

Challenge:	ComicVQA is a visual reasoning benchmark for comics.
Approach:	They propose a comics-based benchmark for evaluating MLLMs on visual reasoning.
Outcome:	The proposed model achieves 62.6% accuracy on Missing Panel Prediction and 46.4% on Panel Sorting, compared to open-source models.

Copied to clipboard

Liangming Pan, Xinyuan Lu, Min-Yen Kan, Preslav Nakov

MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences (2022.emnlp-main)

Challenge:	Existing fact-checking systems lack transparency in their decision-making process, making it difficult for users to comprehend their reasoning process.
Approach:	They propose a Question-guided Multi-hop Fact-Checking system which asks a series of questions critical for verifying a claim.
Outcome:	The proposed model provides a comprehensive report detailing its reasoning process, guided by a sequence of questions, answer pairs, and the source of evidence supporting each question.

Copied to clipboard

Wei Han, Hui Chen, Min-Yen Kan, Soujanya Poria

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

Challenge:	Existing approaches to multimodal learning assume a complete input modality setting, i.e., each modality is either complete or completely missing in both training and test sets.
Approach:	They propose an alignment dynamics learning module based on the theory of optimal transport for missing data imputation and a denoising training algorithm to enhance the quality of iputation and accuracy of model predictions.
Outcome:	The proposed method performs faster and more accurate inferences under different missing conditions and alleviates the overfitting issue.

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.

Identifying Emergent Research Trends by Key Authors and Phrases (C18-1)

Copied to clipboard

Shenhao Jiang, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama

Representation Learning

Challenge:	Existing methods to identify emergent research trends have been employed to generate corpora of large corporata.
Approach:	They propose an embedded trend detection framework which integrates hypothesis that important phrases are written by important authors within a field and vice versa.
Outcome:	The proposed framework outperforms baselines based on text centrality or citations over two large datasets of scientific articles.

When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval (2026.acl-long)

Copied to clipboard

Tongyao Zhu, Huang Chao Ming, Min-Yen Kan

Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Challenge:	Existing multilingual retrievers are largely untested for mixed language queries . sensitivity of dense retrievers to mixed language querying remains poorly understood .
Approach:	They propose to use mixed queries as an interpolation of monolingual embeddings to evaluate retrieval performance.
Outcome:	The proposed model outperforms the best monolingual endpoint in 88/105 cases.

Copied to clipboard

Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou

Programming Languages in NLP

Challenge:	Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach:	They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome:	The proposed framework improves the performance of the proposed benchmark by 28.2%.

Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen (2020.acl-main)

Copied to clipboard

Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Liu, Tat-Seng Chua

Text Generation

Challenge:	a curse of knowledge can impede communication between experts and laymen.
Approach:	They propose a task of expertise style transfer to automate the communication between experts and laymen using an annotated dataset.
Outcome:	The proposed task simplifies professional language and improves accuracy and expertise level of laymen descriptions using simple words.

Zero-shot Fact Verification by Claim Generation (2021.acl-short)

Copied to clipboard

Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

On the Risk of Misinformation Pollution with Large Language Models (2023.findings-emnlp)

Challenge:	Existing methods for fact verification require large datasets, which can be expensive.
Approach:	They propose a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia.
Outcome:	The proposed framework reduces the demand for human-annotated training data and improves a model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples.

Copied to clipboard

Yikang Pan, Liangming Pan, Wenhu Chen, Preslav Nakov, Min-Yen Kan, William Wang

Unsupervised Multi-hop Question Answering by Question Generation (2021.naacl-main)

Challenge:	a recent study demonstrates that large language models can be misused for generating credible-sounding misinformation . however, the ability to produce credible text raises concerns regarding their potential misuse .
Approach:	They propose three defense strategies to mitigate misinformation generated by Large Language Models . they propose a threat model and simulate potential misuse scenarios .
Outcome:	The proposed defense strategies have shown promising results, albeit with costs.

Copied to clipboard

Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

Low-Resource NLP

Challenge:	Existing training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Approach:	They propose an unsupervised framework that generates human-like multi-hop training data from homogeneous and heterogeneously data sources.
Outcome:	The proposed framework achieves 61% and 83% of the supervised learning performance for the HybridQA and HotpotQA datasets.

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

Copied to clipboard

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

Reasoning Robustness of LLMs to Adversarial Typographical Errors (2024.emnlp-main)

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

Esther Gan, Yiran Zhao, Liying Cheng, Mao Yancan, Anirudh Goyal, Kenji Kawaguchi, Min-Yen Kan, Michael Shieh

Robustness in NLP

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting.
Approach:	They develop an algorithm that iteratively samples typos for words that are important to the query and selects the edit that is most likely to succeed in attacking.
Outcome:	The proposed algorithm detects typographical errors in large and closed-source LLMs and shows that they are robust to them.

KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration (2025.findings-emnlp)

Copied to clipboard

Yajing Yang, Tony Deng, Min-Yen Kan

Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations (2024.acl-long)

Challenge:	KAHAN leverages LLMs as domain experts to drive the analysis.
Approach:	They propose a knowledge-augmented hierarchical framework that extracts insights from raw tabular data.
Outcome:	KAHAN outperforms existing frameworks on financial reporting benchmarks on narrative quality and factuality.

Copied to clipboard

Yisong Miao, Hongfu Liu, Wenqiang Lei, Nancy Chen, Min-Yen Kan

ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning (2023.findings-emnlp)

Challenge:	Discursive Socratic Questioning (DISQ) assesses a model's understanding of discourse relations by requiring systematic accuracy over multiple questions.
Approach:	They propose a method that evaluates faithfulness of understanding discourse based on question answering.
Outcome:	The proposed method evaluates the faithfulness of understanding discourse based on question answering.

Copied to clipboard

Yuxi Xie, Guanzhen Li, Min-Yen Kan

Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation (2023.acl-long)

Challenge:	ECHo is a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
Approach:	They propose a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
Outcome:	The proposed framework examines the reasoning capability of current AI systems on three human-centric tasks.

Copied to clipboard

Ibrahim Taha Aksu, Min-Yen Kan, Nancy Chen

Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers (2025.acl-tutorials)

Challenge:	Parameter-Efficient Transfer Learning (PETL) has the potential to address this problem, but it has yet to be applied to the zero-shot domain adaptation.
Approach:	They propose to use descriptions of target domain slots to generate dynamic prefixes that are concatenated to the key and values at each layer’s self-attention mechanism.
Outcome:	The proposed method outperforms previous methods on the MultiWOZ and SGD benchmarks.

Copied to clipboard

Luciana Benotti, Fanny Ducel, Karën Fort, Guido Ivetta, Zhijing Jin, Min-Yen Kan, Seunghun J. Lee, Minzhi Li, Margot Mieskes, Adriana Pagano

MVP-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans? (2024.findings-emnlp)

Challenge:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .
Approach:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .
Outcome:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .

Copied to clipboard

Guanzhen Li, Yuxi Xie, Min-Yen Kan

Visual Data in NLP

Challenge:	Existing LVLMs perform visual perception at multiple levels, but they are not able to perform multi-level tasks.
Approach:	They propose a visual–language benchmark to evaluate LVLMs' perceptions . they use manipulated images to examine how LVLs can perform multi-level tasks .
Outcome:	The proposed model performs poorly on high-level perception tasks, the authors show . they also show that current models do not generalize in understanding semantics of synthetic images .

Interpreting the Robustness of Neural NLP Models to Textual Perturbations (2022.findings-acl)

Copied to clipboard

Yunxiang Zhang, Liangming Pan, Samson Tan, Min-Yen Kan

A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors (2024.emnlp-main)

Challenge:	Modern Natural Language Processing models are sensitive to input perturbations and their performance can decrease when applied to noisy data.
Approach:	They propose to explain the extent to which a model is affected by an unseen textual perturbation by the learnability of the perturbation.
Outcome:	The proposed model is better at identifying a perturbation (higher learnability) but worse at ignoring it (lower robustness).

Copied to clipboard

Naaman Tan, Josef Valvoda, Tianyu Liu, Anej Svete, Yanxia Qin, Min-Yen Kan, Ryan Cotterell

Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework (2020.coling-main)

Challenge:	a relationship exists between the quality of a string and its probability, p(y), under a language model, and the quality and quality of the string.
Approach:	They examine the probability-quality relationship in language models aligned to human preferences through reinforcement learning through human feedback.
Outcome:	The proposed method improves the quality of text sampled from a language model by skewing the model towards high-probability strings.

Copied to clipboard

Akshay Bhola, Kishaloy Halder, Animesh Prasad, Min-Yen Kan

Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure (2020.coling-main)

Challenge:	65% of job descriptions miss describing a significant number of relevant skills, a problem we address with a deep learning model based on a multi-label classification problem .
Approach:	They propose a deep learning model to learn the set of enumerated job skills associated with a job description.
Outcome:	The proposed model improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain.

Copied to clipboard

Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, Bing Qin

Natural Language Interfaces

Challenge:	Multiparty dialog applications such as discourse parsing and meeting summarization are now mainstream research.
Approach:	They propose to annotate a machine reading comprehension dataset with discourse structure built over multiparty dialog using a modified Segmented Discourse Representation Theory (SDRT) style.
Outcome:	The proposed dataset contributes large-scale discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT) style for all of its multiparty dialogs, and achieves only 67.7% F1 on Molweni’s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.

CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability (2023.emnlp-demo)

Copied to clipboard

Yixi Ding, Yanxia Qin, Qian Liu, Min-Yen Kan

Information Extraction & Text Mining

Challenge:	Using a controlled summarization system, we provide a toolkit for scientific summarizing documents.
Approach:	They propose a toolkit for controlled summarization of scientific documents that adjusts key attributes specifically of length and keyword inclusion.
Outcome:	The proposed system generates high-quality summaries based on user preferences, adjusting key attributes specifically of length and keyword inclusion.

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning (2025.findings-naacl)

Copied to clipboard

Xinyuan Lu, Liangming Pan, Yubo Ma, Preslav Nakov, Min-Yen Kan

ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems (2025.findings-naacl)

Challenge:	Current Large Language Models lack ability to understand table structures and apply precise numerical reasoning.
Approach:	They propose a tool-augmented reasoning framework for table-based tasks that integrates LLMs with specialized tools.
Outcome:	The proposed framework improves on the TOOLTAB dataset, a benchmark for LLMs in table–tool integration.

Copied to clipboard

Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li

Natural Language Interfaces

Challenge:	Experimental results show that ChatCRS improves language quality and informativeness by 17% and proactivity by 27%.
Approach:	They propose a framework to decompose the CRS task into several sub-tasks . they propose 'knowledge retrieval agent' and 'goal-planning agent'
Outcome:	The proposed framework improves language quality and informativeness by 17% and proactivity by 27% on two multi-goal CRS datasets.

Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models (2024.emnlp-main)

Copied to clipboard

Do Long, Duong Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy Chen

Re-examining the Role of Schema Linking in Text-to-SQL (2020.emnlp-main)

Challenge:	Existing enhancements of ExpertPrompting improve the large language model generation process.
Approach:	They propose a novel enhancement of ExpertPrompting to improve LLM generation by simulating multiple experts, aggregating their responses and selecting the best among individual and aggregated responses.
Outcome:	The proposed enhancement outperforms ExpertPrompting and comparable baselines in truthfulness, factuality, informativeness, usefulness and harmfulness.

Copied to clipboard

Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua

Programming Languages in NLP

Challenge:	Existing text-to-SQL models treat schema linking as a minor component . Existing solutions treat schema as merely a string component based on string matching .
Approach:	They build a schema linking corpus based on a Spider text-to-SQL dataset . they find schema linking is the crux for the current text- to-Sql task .
Outcome:	The proposed model performs well on the Spider text-to-SQL dataset despite its simplicity.

Doolittle: Benchmarks and Corpora for Academic Writing Formalization (2023.emnlp-main)

Copied to clipboard

Shizhe Diao, Yongyu Lei, Liangming Pan, Tianqing Fang, Wangchunshu Zhou, Sedrick Keh, Min-Yen Kan, Tong Zhang

Reliability Testing for Natural Language Processing Systems (2021.acl-long)

Challenge:	Existing methods of language refinement focus on narrow, specific linguistic features within isolated sentences, such as grammatical errors and improper word use.
Approach:	They propose a task to improve the overall quality of academic writing at paragraph level by integrating automatic feedback into the training process.
Outcome:	The proposed task improves the overall quality of formal academic writing at the paragraph level.

Copied to clipboard

Samson Tan, Shafiq Joty, Kathy Baxter, Araz Taeihagh, Gregory A. Bennett, Min-Yen Kan

Semantic Graphs for Generating Deep Questions (2020.acl-main)

Challenge:	a lack of rigorous testing and ML implicit assumption of identical training and testing distributions may result in systems that discriminate against minorities.
Approach:	They argue that reliability testing is needed to address the issue of demographics . they argue that adversarial attacks can be reframed for this goal .
Outcome:	The proposed framework will enable rigorous and targeted testing and aid in the enactment and enforcement of industry standards.

Copied to clipboard

Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs (2025.naacl-long)

Challenge:	Existing research has focused on generating factoid questions relevant to one fact obtainable from a single sentence.
Approach:	They propose a framework that first constructs a semantic-level graph and then encodes it by introducing an attention-based GGNN.
Outcome:	The proposed framework captures the global structure of the document and facilitates reasoning over multiple facts.

Copied to clipboard

Do Xuan Long, Ngoc-Hai Nguyen, Tiviatis Sim, Hieu Dao, Shafiq Joty, Kenji Kawaguchi, Nancy F. Chen, Min-Yen Kan

Challenge:	Using format-following capabilities, state-of-the-art large language models (LLMs) can be leveraged to tailor outputs to specific task formats.
Approach:	They propose to define a format bias evaluation metric and establish effective strategies to reduce it.
Outcome:	The proposed evaluation reduces the variance in ChatGPT’s performance among wrapping formats from 235.33 to 0.71 (%2)

Domain Divergences: A Survey and Empirical Analysis (2021.naacl-main)

Copied to clipboard

Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann

SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables (2023.emnlp-main)

Challenge:	Existing literature on divergence measures is lacking in predicting performance of models in new domains.
Approach:	They propose a taxonomy of divergence measures consisting of three classes — Information-theoretic, Geometric, and Higher-order measures and identify the relationships between them.
Outcome:	The proposed measures are based on three novel use-cases and identify that they are prevalent in three domains and higher-order measures are more common in two.

Copied to clipboard

Xinyuan Lu, Liangming Pan, Qian Liu, Preslav Nakov, Min-Yen Kan

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines (2025.findings-acl)

Challenge:	Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence.
Approach:	They present a dataset of 1.2K expert-verified scientific claims that require compositional reasoning for verification.
Outcome:	The proposed model outperforms existing models in table-based pretraining models and large language models.

Copied to clipboard

Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong, Anh Tuan Luu, Kenji Kawaguchi, Shafiq Joty, Min-Yen Kan, Nancy F. Chen

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

Challenge:	In-context learning is an important but not fully understood ability of pre-trained large language models.
Approach:	They propose a tool that generates two streams of guidelines capturing task language and format distributions and prompts them to define them by prompting.
Outcome:	The proposed model improves both strong open- and closed-source LLMs by over 5% in both zero- and few-shot settings.

Copied to clipboard

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

Understanding Ethics in NLP Authoring and Reviewing (2023.eacl-tutorials)

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

Luciana Benotti, Karën Fort, Min-Yen Kan, Yulia Tsvetkov

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation (2026.acl-long)

Challenge:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues .
Approach:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . the methodology is interactive and participatory, including case studies and working in groups .
Outcome:	This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . the methodology is interactive and participatory, including case studies and working in groups.

Copied to clipboard

Jiaying Wu, Zihang Fu, Haonan Wang, Fanxiao Li, Jiafeng Guo, Preslav Nakov, Min-Yen Kan

NNOSE: Nearest Neighbor Occupational Skill Extraction (2024.eacl-long)

Challenge:	X (formerly Twitter) users can flag misleading posts, attach contextual notes, and rate the notes’ helpfulness, but there is a significant latency in Community Notes, which is unable to provide accurate notes.
Approach:	They propose a framework that augments Community Notes for faster and more reliable health misinformation governance.
Outcome:	The proposed framework outperforms human contributors in correctness, helpfulness, and evidence utility in health misinformation surges.

Copied to clipboard

Mike Zhang, Rob Goot, Min-Yen Kan, Barbara Plank

Information Extraction & Text Mining

Challenge:	a new method for extracting occupational skills from text is needed to overcome the scarcity of skills across datasets.
Approach:	They propose a method that leverages multiple datasets to extract occupational skills from text . they propose NNOSE to extract neighboring skills from other datasets .
Outcome:	The proposed method improves infrequent skill extraction without additional fine-tuning.

GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding (2022.acl-long)

Copied to clipboard

Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan

The ACL OCL Corpus: Advancing Open Science in Computational Linguistics (2023.emnlp-main)

Challenge:	Existing approaches to zero-shot cross-lingual spoken language understanding rely on shared parameters, which can only perform implicit alignment across languages.
Approach:	They propose a global-local contrastive learning framework to achieve a fine-grained cross-lingual transfer . they employ bilingual dictionaries to construct multilingual views of the same utterance .
Outcome:	Experiments on MultiATIS++ show that GL-CLeF achieves the best performance . GL is based on dictionaries and encourages representations to be more similar than negative example pairs .

Copied to clipboard

Shaurya Rohatgi, Yanxia Qin, Benjamin Aw, Niranjana Unnithan, Min-Yen Kan

Challenge:	ACL OCL is a scholarly corpus derived from the ACL Anthology . it provides metadata, PDF files, citation graphs and additional structured full texts .
Approach:	They present ACL OCL, a scholarly corpus derived from the ACL Anthology . it integrates metadata, PDF files, citation graphs and additional structured full texts . they highlight how it applies to observe trends in computational linguistics .
Outcome:	The ACL OCL spans seven decades and contains 73,285 papers . the scholarly corpus is based on the ACL Anthology and is available from HuggingFace .

UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking (2024.findings-naacl)

Copied to clipboard

Chuang Li, Yan Zhang, Min-Yen Kan, Haizhou Li

Low-Resource NLP

Challenge:	Existing methods for zero-shot dialogue state tracking (DST) ignore unlabelled data in the target domain.
Approach:	They propose to transform zero-shot dialogue state tracking into few-shot DST by utilising unlabelled data via joint and self-training methods.
Outcome:	The proposed method improves joint goal accuracy by 8% on general language models in zero-shot scenarios, and can be used in many domains.

TraVLR: Now You See It, Now You Don’t! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning (2023.eacl-main)

Copied to clipboard

Keng Ji Chow, Samson Tan, Min-Yen Kan

Discursive Circuits: How Do Language Models Understand Discourse Relations? (2025.emnlp-main)

Challenge:	Existing visio-linguistic (V+L) models do not represent visual and linguistic concepts in a unified space.
Approach:	They propose to use cross-modal transfer to evaluate the extent to which visio-linguistic (V+L) representations are represented in a unified space.
Outcome:	The proposed evaluation settings include cross-modal transfer and a global accuracy score on the entire dataset making the specific sources of success and failure difficult to diagnose.

Copied to clipboard

Yisong Miao, Min-Yen Kan