Papers by Peng Chang

Mitigating Bias for Question Answering Models by Tracking Bias Influence (2024.naacl-long)

Challenge:	Existing models for event extraction require expensive human annotations.
Approach:	They propose a data-efficient event extraction model that formulates event extraction as a conditional generation problem.
Outcome:	The proposed model can be trained with only a few labeled examples.

Copied to clipboard

Mingyu Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng

Question Answering

Challenge:	Existing literature observes bias in question answering (QA) models, but there is no method to mitigate it.
Approach:	They propose an approach to mitigate the bias of question answering models by observing the influence of a query instance on another instance.
Outcome:	The proposed method reduces bias level in all 9 bias categories while maintaining comparable QA accuracy.

Contextual Label Projection for Cross-Lingual Structured Prediction (2024.naacl-long)

Copied to clipboard

Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, Nanyun Peng

Multilinguality

Challenge:	Prior work favors simplified label translation or relying on word-level alignments for label projection.
Approach:	They propose a novel approach CLaP which translates text to target language and performs contextual translation on the labels using the translated text as the context.
Outcome:	The proposed approach improves translation accuracy on two prediction tasks and shows 2.4 F1 improvement for EAE and 1.4 F1 for named entity recognition.

BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression (2025.findings-naacl)

Copied to clipboard

Yuankai Li, Jia-Chen Gu, Di Wu, Kai-Wei Chang, Nanyun Peng

Information Retrieval

Challenge:	Existing approaches to augment language models with external knowledge but they are limited by static nature of pre-training data.
Approach:	They propose a lightweight approach that compresses retrieved documents into highly dense textual summaries to integrate into in-context RAG.
Outcome:	The proposed approach reduces latency and costs while achieving high performance in open-domain questions.

Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training (2021.emnlp-main)

Copied to clipboard

Kuan-Hao Huang, Wasi Ahmad, Nanyun Peng, Kai-Wei Chang

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks (2026.acl-long)

Challenge:	Pre-trained multilingual language encoders do not precisely align words and phrases across languages.
Approach:	They propose a learning strategy for training robust models by drawing connections between adversarial examples and failure cases of zero-shot cross-lingual transfer.
Outcome:	The proposed model can achieve good performance even if representations of different languages are not aligned well.

Copied to clipboard

Hyeonjeong Ha, Qiusi Zhan, Jeonghwan Kim, Dimitrios Bralios, Saikrishna Sanniboina, Nanyun Peng, Kai-Wei Chang, Daniel Kang, Heng Ji

Robustness in NLP

Challenge:	Existing research exposes multimodal large language models to knowledge poisoning attacks . localized poisoning attack achieves up to 56% success rate even under restricted access . globalized poison attack completely disrupts model generation to 0% accuracy with just one poisoned content.
Approach:	They propose a framework to study the vulnerability of multimodal RAG under knowledge poisoning attacks.
Outcome:	The proposed framework exploits two new attack strategies on multimodal RAGs under knowledge poisoning.

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning (2024.findings-emnlp)

Copied to clipboard

Silin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng, Kai-Wei Chang

Towards Fine-grained Text Sentiment Transfer (P19-1)

Challenge:	Existing path planning algorithms suffer from significant computational and memory inefficiencies as the state space grows . large language models excel in environmental analysis but fall short in detailed spatial and temporal reasoning .
Approach:	They propose a new path planning method that synergistically combines A* and LLMs to improve pathfinding efficiency.
Outcome:	The proposed method improves pathfinding efficiency while maintaining integrity of path validity in large-scale scenarios.

Copied to clipboard

Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui, Xu Sun

Sentiment Analysis

Challenge:	Existing methods for fine-grained text sentiment transfer only reverse the sentiment polarity of text, but they lack a robust and parallel learning algorithm.
Approach:	They propose a novel fine-grained text sentiment transfer task that revises a sequence to satisfy a given sentiment intensity while preserving the original semantic content.
Outcome:	The proposed model outperforms existing methods by a large margin in automatic evaluation and human evaluation.

Beyond Facts- Benchmarking Distributional Reading Comprehension in Large Language Models (2026.findings-acl)

Copied to clipboard

Pei-Fu Guo, Ya An Tsai, Chun-Chia Hsu, Kai-Xin Chen, Yun-Da Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin

LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs (2026.acl-long)

Challenge:	Existing reading comprehension benchmarks focus on factual information, but many real-world tasks require distributional knowledge expressed across text.
Approach:	They propose a reading comprehension benchmark for LLMs to evaluate their ability to infer distributional knowledge from natural language.
Outcome:	Experiments with multiple LLMs show that the model outperforms baselines, but performance varies widely across distribution types and characteristics.

Copied to clipboard

Pei-Fu Guo, Yun-Da Tsai, Chun-Chia Hsu, Kai-Xin Chen, Ya An Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin

Multilinguality

Challenge:	Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior exposure during pre-training.
Approach:	They propose a pipeline to isolate and measure cross-lingual knowledge transfer by identifying self-contained, time-sensitive knowledge entities from real-world domains and generating factual questions.
Outcome:	The proposed pipeline analyzes multiple LLMs across five languages and shows that cross-lingual transfer is strongly influenced by linguistic distance and often asymmetric across language directions.

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness (2024.emnlp-main)

Copied to clipboard

Tanmay Parekh, Jeffrey Kwan, Jiarui Yu, Sparsh Johri, Hyosang Ahn, Sreya Muppalla, Kai-Wei Chang, Wei Wang, Nanyun Peng

Multilinguality

Challenge:	Prior studies focused on English posts to provide early warnings for epidemic prediction, but these work focused on non-English posts.
Approach:	They propose a multilingual event extraction framework for extracting epidemic event information for any disease and language using 5.1K tweets in four languages.
Outcome:	The proposed framework can provide epidemic warnings for COVID-19 in its earliest stages in Dec 2019 (3 weeks before global discussions) and aggregate community epidemic discussions like symptoms and cure measures, aiding misinformation detection and public attention monitoring.

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints (2024.findings-emnlp)

Copied to clipboard

Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs (2024.findings-emnlp)

Challenge:	Recent studies have shown that LLMs struggle with instructions containing multiple constraints.
Approach:	They propose a self-correction pipeline that decomposes the original instruction into a list of constraints and uses a Critic model to decide when and where the LLM’s response needs refinement.
Outcome:	The proposed model outperforms GPT-4 on RealInstruct and IFEval even with weak feedback.

Copied to clipboard

Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang

Control Large Language Models via Divide and Conquer (2024.emnlp-main)

Challenge:	Visual programs are executable code generated by large language models to address visual reasoning problems.
Approach:	They propose a critic-refiner framework that localizes and debugs visual programs by tracking execution step by step.
Outcome:	The proposed framework detects and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy.

Copied to clipboard

Bingxuan Li, Yiwei Wang, Tao Meng, Kai-Wei Chang, Nanyun Peng

Rumor Detection on Social Media with Crowd Intelligence and ChatGPT-Assisted Networks (2023.emnlp-main)

Challenge:	Lexically Constrained Generation (LCG) is a crucial task of text generation.
Approach:	They propose a Divide and Conquer Generation strategy to enhance LLMs' performance in Lexically Constrained Generation with prompt-based controlling.
Outcome:	The proposed strategy shows 90% improvement on the most challenging LCG task.

Copied to clipboard

Chang Yang, Peng Zhang, Wenbo Qiao, Hui Gao, Jiaming Zhao

SNaRe: Domain-aware Data Generation for Low-Resource Event Detection (2025.emnlp-main)

Challenge:	Existing research on rumor detection challenges the expressive power of text encoding sequences, and insufficient mining of semantic structural information.
Approach:	They propose a Crowd Intelligence-based semantic feature learning module to capture textual content’s sequential and hierarchical features and a knowledge-based structural mining module that leverages ChatGPT for knowledge enhancement.
Outcome:	The proposed system achieves performance improvement in rumor detection tasks validating the effectiveness and rationality of using large language models as auxiliary tools.

Copied to clipboard

Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar, Artin Kim, I-Hung Hsu, Kai-Wei Chang, Nanyun Peng

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning (2025.emnlp-main)

Challenge:	Existing methods for ED struggle with label noise and domain drift when applied to specialized domains.
Approach:	They propose a domain-aware synthetic data generation framework composed of three components: Scout, Narrator, and Refiner.
Outcome:	The proposed framework outperforms baseline approaches on three diverse domain ED datasets and achieves average F1 gains of 3-7% in the zero-shot/few-shot settings and 4-20% improvement for multilingual generation.

Copied to clipboard

Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi, Kai-Wei Chang, Nanyun Peng

Low-Resource NLP

Challenge:	Understanding the complex event ontology, extracting domain-specific triggers from the passage, and structuring them appropriately overloads and limits the utility of Large Language Models (LLMs).
Approach:	They propose a divergent-convergent reasoning framework that decouples the task of ED using Dreamer and Grounder.
Outcome:	The proposed framework outperforms baselines on six datasets across five domains and nine LLMs, achieving 4–7% average gains over the best baseline.

SYNTHIA: Novel Concept Design with Affordance Composition (2025.acl-long)

Copied to clipboard

Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-Wei Chang, Heng Ji

GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles (2023.acl-long)

Challenge:	Existing studies on concept design using text-to-image models have enabled rapid ideation of novel visual concepts.
Approach:	They propose a framework for generating novel, functionally coherent designs based on desired affordances by decomposing concepts into parts and affordance . they also develop a curriculum learning scheme that fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty.
Outcome:	The proposed framework outperforms state-of-the-art models for novelty and functional coherence in human evaluation.

Copied to clipboard

Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, Nanyun Peng

Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM (2024.emnlp-main)

Challenge:	Existing benchmarking datasets for Event Argument Extraction (EAE) cover less than 40 event types and 25 entity-centric argument roles.
Approach:	They propose to use a large and diverse EAE ontology to create a semantic role labeling dataset for EAE that incorporates 115 events and 220 argument roles.
Outcome:	The proposed ontology concludes with 115 events and 220 argument roles, with a significant portion of roles not being entities.

Copied to clipboard

Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung

You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL (2025.naacl-long)

Challenge:	Contrastive decoding (CD) improves the next-token distribution of a large expert language model (LM) using a small amateur LM.
Approach:	They propose a new unsupervised decoding method called Asymptotic Probability Decoding (APD) that extrapolates the probability curves from the LMs of different sizes to infer the asymptototic probabilities from an infinitely large LM.
Outcome:	The proposed method improves the next-token distribution of a large expert language model using a small amateur LM.

Copied to clipboard

Hideo Kobayashi, Wuwei Lan, Peng Shi, Shuaichen Chang, Jiang Guo, Henghui Zhu, Zhiguo Wang, Patrick Ng

Programming Languages in NLP

Challenge:	Existing text-to-SQL systems encode the same schema for every question, resulting in unnecessary high inference cost and missing crucial database knowledge.
Approach:	They propose a paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference.
Outcome:	The proposed paradigm significantly reduces the input token length by 66%-98% and outperforms traditional systems on three benchmarks.

Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks (2023.emnlp-main)

Copied to clipboard

Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng

ORANGE: Text-video Retrieval via Watch-time-aware Heterogeneous Graph Contrastive Learning (2023.emnlp-industry)

Challenge:	Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models on diverse tasks with instructions.
Approach:	They propose a framework to identify informative tasks and then actively tune models on selected tasks.
Outcome:	The proposed method outperforms baseline strategies for task selection on NIV2 and Self-Instruct datasets.

Copied to clipboard

Yucheng Lin, Tim Chang, Yaning Chang, Jianqiang Ma, Donghui Li, Ting Peng, Zang Li, Zhiyi Zhou, Feng Wang

“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters (2023.findings-emnlp)

Challenge:	Existing methods for text-video retrieval focus on informative representations and delicate matching mechanisms, but real-world scenarios often involve brief, ambiguous queries and low-quality videos.
Approach:	They propose a novel method to learn informative embeddings for queries and videos . they use a watch-time-aware contrastive learning paradigm to capture dependencies .
Outcome:	The proposed method is effective in a real-world video-search service.

Copied to clipboard

Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng

Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing (D19-1)

Challenge:	Large Language Models (LLMs) are an effective tool to assist individuals in writing documents.
Approach:	They examine gender biases in large language models (LLMs)-generated reference letters . they find that models are biased because they are hallucinated .
Outcome:	The proposed model-generated reference letters are evaluated on 2 popular LLMs- ChatGPT and Alpaca.

Copied to clipboard

Tao Meng, Nanyun Peng, Kai-Wei Chang

Syntactic Text Processing

Challenge:	Existing work on cross-lingual dependency parsing focuses on capturing commonalities between source and target languages and overlooking the potential to leverage the linguistic properties of the target languages to facilitate the transfer.
Approach:	They propose to use Lagrangian relaxation and posterior regularization techniques to conduct inference with corpus-statistics constraints to capture commonalities between source and target languages.
Outcome:	The proposed algorithms improve on 15 and 17 out of 19 target languages.

BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning (2026.findings-acl)

Copied to clipboard

Jia-Chen Gu, Junyi Zhang, Di Wu, Yuankai Li, Kai-Wei Chang, Nanyun Peng

Reasoning

Challenge:	Experiments show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models.
Approach:	They propose a universal, lightweight compressor that distills relevant evidence from retrieved documents into a concise summary for seamless integration into in-context RAG.
Outcome:	Experiments on four open-domain multi-hop question-answering datasets show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models.

Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025.acl-long)

Copied to clipboard

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-Wei Chang

Text Classification

Challenge:	Recent research shows that vertical text input significantly degrades the accuracy of large language models (LLMs) in text classification tasks.
Approach:	They investigate the impact of vertical text input on the performance of LLMs . they find that chain of thought reasoning does not help LLM recognize vertical input .
Outcome:	The proposed model can significantly mislead models, posing a risk of bypassing detection in real-world scenarios involving harmful or sensitive information.

On Measures of Biases and Harms in NLP (2022.findings-aacl)

Copied to clipboard

Sunipa Dev, Emily Sheng, Jieyu Zhao, Aubrie Amstutz, Jiao Sun, Yu Hou, Mattie Sanseverino, Jiin Kim, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang

Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning (2021.emnlp-main)

Challenge:	Recent studies show that natural language processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Approach:	They propose a framework for harms and questions to help practitioners understand biases . they propose measurable measures to detect and mitigate biased groups .
Outcome:	The proposed framework provides a framework for harms and questions for practitioners to answer to guide the development of bias measures.

Copied to clipboard

Da Yin, Liunian Harold Li, Ziniu Hu, Nanyun Peng, Kai-Wei Chang

Reasoning

Challenge:	Generally, commonsense knowledge is correlated with culture and geographic locations and is only shared locally.
Approach:	They construct a Geo-Diverse Visual Commonsense Reasoning dataset to test vision-and-language models’ ability to understand cultural and geo-location-specific commonsense.
Outcome:	The proposed models perform better in non-Western regions including East Asia, South Asia, and Africa than in the Western regions.

Style-News: Incorporating Stylized News Generation and Adversarial Verification for Neural Fake News Detection (2024.eacl-long)

Copied to clipboard

Wei-Yao Wang, Yu-Chieh Chang, Wen-Chih Peng

Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021.findings-acl)

Challenge:	Using generative models, the issues of producing hallucinatory contents have been raised in various domains, e.g., law, writing.
Approach:	They propose a style-aware neural news generator that mimics the style of real news to deceive people by identifying which publisher the style corresponds to and training a model to detect fake news.
Outcome:	The proposed framework outperforms state-of-the-art models in terms of fluency, content preservation, and style adherence.

Copied to clipboard

Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang

Structured Data in NLP

Challenge:	Existing methods for table-to-text generation suffer from poor faithfulness and low coverage.
Approach:	They propose a method that combines Autoregressive and Non-Autoregressive generation to generate a table-to-text from a key-value table using a skeleton and an edit-based non-autoregressively generation model.
Outcome:	The proposed method outperforms the existing methods on WikiPerson and WikiBio datasets on coverage and faithfulness.

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism (2025.acl-long)

Copied to clipboard

Congzhi Zhang, Jiawei Peng, Zhenglin Wang, Yilong Lai, Haowen Sun, Heng Chang, Fei Ma, Weijiang Yu

QUDSELECT: Selective Decoding for Questions Under Discussion Parsing (2024.emnlp-main)

Challenge:	Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is constrained.
Approach:	They propose a training-free approach that enhances Reasoning in Large Vision-Language Models . they propose integrating Monte Carlo Tree Search and Self-Reward mechanisms into the reasoning tree .
Outcome:	The proposed approach surpasses current prompting methods and secures state-of-the-art performance across three multimodal reasoning benchmarks.

Copied to clipboard

Ashima Suvarna, Xiao Liu, Tanmay Parekh, Kai-Wei Chang, Nanyun Peng

Challenge:	Question Under Discussion (QUD) uses implicit questions to reveal discourse relationships between sentences.
Approach:	They propose a framework that selectively decodes the QUD dependency structures considering the QUC criteria.
Outcome:	The proposed framework outperforms the state-of-the-art baseline models by 9% in human evaluation and 4% in automatic evaluation.

Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)

Copied to clipboard

Chang Shu, Yusen Zhang, Xiangyu Dong, Peng Shi, Tao Yu, Rui Zhang

Text Generation

Challenge:	Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency.
Approach:	They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control.
Outcome:	The proposed framework enhances logic consistency and human evaluation on two benchmark datasets.

Rethink Rumor Detection in the Era of LLMs: A Review (2025.findings-emnlp)

Copied to clipboard

Chang Yang, Peng Zhang, Jing Zhang, Hui Gao, Changhao Song

Hierarchical User Intent Inference with Knowledge Graph Grounding (2026.findings-eacl)

Challenge:	rumor detection has been reshaped by large language models (LLMs) this paper proposes a Cognition-Interaction-Behavior (CIB) framework for rumour detection based on collective intelligence .
Approach:	They propose a Cognition-Interaction-Behavior framework for rumor detection based on collective intelligence and explore synergistic relationship between LLMs and collective intelligence in rumour governance.
Outcome:	The proposed framework unifies existing methods and reveals synergistic relationship between LLMs and collective intelligence in rumor governance.

Copied to clipboard

Tzu-Cheng Peng, Chien Chin Chen, Yung-Chun Chang

Knowledge Representation

Challenge:	Existing large language models lack structured grounding and do not capture nuanced intent expression.
Approach:	They propose a Hierarchical Intent Inference framework that first predicts fine-grained aspect ratings and then generates natural language intent statements guided by contextual subgraphs retrieved from a domain-specific knowledge graph.
Outcome:	The proposed framework outperforms strong LLM and encoder-based baselines on a hotel review dataset.

Re-ReST: Reflection-Reinforced Self-Training for Language Agents (2024.emnlp-main)

Copied to clipboard

Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu, Kai-Wei Chang, Nanyun Peng

Natural Language Interfaces

Challenge:	Existing methods to fine tune language agents with reasoning-action trajectories require high-quality model-generated samples, which are hard to obtain for challenging language agent tasks.
Approach:	They propose a method to employ reflection during inference without ground-truth feedback to improve agents more autonomously.
Outcome:	The proposed method improves self-training performance on open-source language agents by 7.6% and 14.1% respectively.

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs (2026.findings-acl)

Copied to clipboard

Wu Zhengxian, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Xue Yiming

Robustness in NLP

Challenge:	Existing black-box instruction backdoors can detect poisoned inputs, but fail to recover correct outputs once the backdoor is activated.
Approach:	They propose a soft label mechanism and key-extraction-guided CoT-based defense against instruction backdoors in APIs (SLIP) they propose KCOT-based model to extract task-relevant keywords and phrases rather than only considering the single trigger or overall text semantics.
Outcome:	The proposed model reduces the average attack success rate to 25.13% and improves clean accuracy to 87.15% and outperforms state-of-the-art black-box defenses.

Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis (2022.findings-emnlp)

Copied to clipboard

Iek-Heng Chu, Ziyi Chen, Xinlu Yu, Mei Han, Jing Xiao, Peng Chang

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction (2024.findings-acl)

Challenge:	Existing approaches to multimodal speech emotion recognition and sentiment analysis have not improved results due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining.
Approach:	They propose a deep-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and stage-wise cross-mod pretraining scheme to facilitate cross-modulation.
Outcome:	The proposed method exceeds benchmarks on public IEMOCAP emotion and CMU-MOSEI sentiment datasets by a large margin.

Copied to clipboard

Kuan-Hao Huang, I-Hung Hsu, Tanmay Parekh, Zhiyu Xie, Zixuan Zhang, Prem Natarajan, Kai-Wei Chang, Nanyun Peng, Heng Ji

Deciphering Rumors: A Multi-Task Learning Approach with Intent-aware Hierarchical Contrastive Learning (2024.emnlp-main)

Challenge:	Recent studies suggest that event extraction evaluations may not accurately reflect the true performance.
Approach:	They propose a standardized, fair, and reproducible benchmark for event extraction . they use standardized scripts and splits for 16 datasets spanning eight domains .
Outcome:	The proposed benchmarks show that they struggle to achieve satisfactory performance.

Copied to clipboard

Chang Yang, Peng Zhang, Hui Gao, Jing Zhang

Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction (2022.acl-long)

Challenge:	Social networks are rife with noise and misleading information, presenting multifaceted challenges for rumor detection.
Approach:	They propose a new multi-task learning framework that mines latent intentions and rumor semantic features . they propose to use event-level and intent-level strategies to establish cognitive anchors .
Outcome:	The proposed framework improves the effectiveness of rumor detection and addresses the challenges present in the field.

Copied to clipboard

Kuan-Hao Huang, I-Hung Hsu, Prem Natarajan, Kai-Wei Chang, Nanyun Peng

LLM-SLM Collaborative Framework of Idiomatic Expression Generation (2026.acl-long)

Challenge:	Existing models for zero-shot cross-lingual event argument extraction are based on pre-trained generative language models.
Approach:	They propose to use pre-trained generative language models to generate sentences that fill in a template with arguments extracted from the input passage.
Outcome:	The proposed model outperforms the current state-of-the-art models on zero-shot cross-lingual EAE.

Copied to clipboard

Hui Gao, Changhao Song, Peng Zhang, Jing Zhang, Chang Yang, Liuxian Ge

“Nice Try, Kiddo”: Investigating Ad Hominems in Dialogue Responses (2021.naacl-main)

Challenge:	Existing methods for idiomatic expression generation lack parallel data and manual annotations.
Approach:	They propose an iterative LLM-SLM collaborative framework that replaces human supervision for idiomatic expression data generation.
Outcome:	The proposed framework outperforms DeepSeek-R1 in Chinese Idiom Polishing with a 25.2% improvement in accuracy.

Copied to clipboard

Emily Sheng, Kai-Wei Chang, Prem Natarajan, Nanyun Peng

Dialogue Systems & Conversational Agents

Challenge:	Ad hominem attacks target a person's character instead of the position the person is maintaining.
Approach:	They propose to use salient n-gram similarity as a soft constraint to reduce the amount of ad hominems generated in Twitter conversations.
Outcome:	The proposed method reduces the amount of ad hominems generated in human and dialogue system responses to English Twitter posts by using salient n-gram similarity as a soft constraint.

Towards Robust Speech Representation Learning for Thousands of Languages (2024.emnlp-main)

Copied to clipboard

William Chen, Wangyou Zhang, Yifan Peng, Xinjian Li, Jinchuan Tian, Jiatong Shi, Xuankai Chang, Soumi Maiti, Karen Livescu, Shinji Watanabe

Robustness in NLP

Challenge:	XEUS is a cross-lingual encoder for universal speech that can be trained on 1 million hours of data across 4057 languages.
Approach:	They propose a Cross-lingual Encoder for Universal Speech that can be trained on 1 million hours of data across 4057 languages and a newly created corpus of 7400+ hours from 4057 .
Outcome:	The proposed model outperforms state-of-the-art models on several benchmarks and outperfies MMS 1B and w2v-BERT 2.0 v2 by 0.8% and 4.4% respectively.

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (2024.emnlp-main)

Copied to clipboard

Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding (2025.coling-main)

Challenge:	Existing approaches to fine tune LLMs produce unsafe responses and unreliable reasoning, but this solution introduces substantial time and space overhead due to the separate models required.
Approach:	They propose to insert extra parameters into transformer architecture to predict calibration signals along with original LLM output.
Outcome:	The proposed model reduces time and space costs while enabling seamless online deployment.

Copied to clipboard

Cheng Wang, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang

Medical Vision-Language Pre-Training for Brain Abnormalities (2024.lrec-main)

Challenge:	Existing methods analyze training data with member and non-member contexts, overlooking potential insights from both member and not-member.
Approach:	They propose a method that leverages asymmetric distributional shifts induced by member and non-member contexts through contrastive decoding to enhance membership inference.
Outcome:	The proposed approach outperforms the current state-of-the-art on the WikiMIA benchmark and is robust against various text manipulation techniques.

Copied to clipboard

Masoud Monajatipoor, Zi-Yi Dou, Aichi Chien, Nanyun Peng, Kai-Wei Chang

Visual Data in NLP

Challenge:	Existing vision-language models lack expertise for medical applications due to the scarcity and complexity of data.
Approach:	They propose a pipeline to collect medical image-text aligned data for pretraining from public resources such as PubMed and build a high-performance vision-language model tailored to specific medical tasks.
Outcome:	The proposed model is based on a large brain image-text dataset and will be released to the public.

Prompt Tuning for Unified Multimodal Pretrained Models (2023.findings-acl)

Copied to clipboard

Hao Yang, Junyang Lin, An Yang, Peng Wang, Chang Zhou

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue (2024.emnlp-main)

Challenge:	Prompt tuning has demonstrated success in natural language pretraining and even vision pretraining.
Approach:	They propose to apply prompt tuning to a unified sequence-to-sequence pretrained model by adding a sequence of learnable embeddings to each layer and finetuning the pretrained models on downstream tasks.
Outcome:	The proposed method outperforms other parameter-efficient tuning methods on multimodal models and is robust against adversarial attacks.

Copied to clipboard

Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, Nanyun Peng

On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing (N19-1)

Challenge:	Existing methods that edit large language models with updated knowledge can cause side effects on the general abilities of LLMs such as reasoning, natural language inference, and question answering.
Approach:	They propose to regularize the edit update weights by imposing constraints on their complexity based on the RElative Change in weighT.
Outcome:	The proposed method can significantly mitigate the side effects while maintaining over 94% editing performance.

Copied to clipboard

Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, Nanyun Peng

Cross-Lingual Transfer

Challenge:	Existing studies on crosslingual transfer have focused on word-level information sharing, but words are not independent in sentences; their combinations form larger linguistic units, known as context.
Approach:	They propose to use orderagnostic models to transfer word order to distant languages . they train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages.
Outcome:	The proposed model performs better on languages with different word orders than on other languages.

Reusing Transferable Weight Increments for Low-resource Style Generation (2024.emnlp-main)

Copied to clipboard

Chunzhen Jin, Eliot Huang, Heng Chang, Yaqi Wang, Peng Cao, Osmar Zaiane

Low-Resource NLP

Challenge:	Text style transfer (TST) is crucial in natural language processing, aiming to endow text with a new style without altering its meaning.
Approach:	They propose a framework to use style features in weight increments to transfer low-resource styles effectively.
Outcome:	The proposed framework achieves remarkable performance across different backbones, achieving particularly effective results in low-resource scenarios.

Towards Controllable Biases in Language Generation (2020.findings-emnlp)

Copied to clipboard

Emily Sheng, Kai-Wei Chang, Prem Natarajan, Nanyun Peng

Text Generation

Challenge:	a new method to induce societal biases in natural language generation is being developed . a method to equalize the amount of biased text across demographics is effective .
Approach:	They propose a method to induce societal biases in natural language generation by using demographic inequalities.
Outcome:	The proposed method is effective at equalizing biases across demographics while generating less negatively biased text overall.

Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)

Copied to clipboard

Hritik Bansal, Ashima Suvarna, Gantavya Bhatt, Nanyun Peng, Kai-Wei Chang, Aditya Grover

METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling (2025.acl-long)

Challenge:	Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models.
Approach:	They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs.
Outcome:	The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets.

Copied to clipboard

Bingxuan Li, Yiwei Wang, Jiuxiang Gu, Kai-Wei Chang, Nanyun Peng

TAGPRIME: A Unified Framework for Relational Structure Extraction (2023.acl-long)

Challenge:	Chart generation requires strong visual design skills and precise coding capabilities that embed the desired visual properties into code.
Approach:	They propose a vision-language model-based multi-agent framework for effective automatic chart generation.
Outcome:	The proposed framework achieves a 5.2% improvement in the F1 score over the current best chart generation task.

Copied to clipboard

I-Hung Hsu, Kuan-Hao Huang, Shuning Zhang, Wenxin Cheng, Prem Natarajan, Kai-Wei Chang, Nanyun Peng

T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Challenge:	Existing models for natural language processing (NLP) do not address common tasks.
Approach:	They propose to take a unified view of all the tasks and introduce a model that appends priming words about the condition to the input text.
Outcome:	The proposed model is based on ten datasets across five different languages and covers ten tasks that cover ten languages.

Copied to clipboard

Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li

Structured Data in NLP

Challenge:	Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach:	They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome:	The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems (2023.findings-emnlp)

Copied to clipboard

Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in Large Language Models enable them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
Approach:	They propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a model that incorporates both generic and specific personas.
Outcome:	The proposed model systematically measures persona biases in harmful expression and harmful agreement.

DRS: Deep Question Reformulation With Structured Output (2025.findings-acl)

Copied to clipboard

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang

Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)

Challenge:	Existing models like GPT-3 and Instruct-GPT lack the ability to reformulate unanswerable questions.
Approach:	They propose a zero-shot method that combines the strengths of LLMs with a DFS-based algorithm to iteratively explore potential entity combinations and constrain outputs using predefined entities.
Outcome:	The proposed method outperforms all baselines, including the GPT-3.5 model, on the unanswerable question reformulation task.

Copied to clipboard

Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric Yang, Kuan-Hao Huang, Wei Wang, Nanyun Peng, Kai-Wei Chang

Consistency Rating of Semantic Transparency: an Evaluation Method for Metaphor Competence in Idiom Understanding Tasks (2025.coling-main)

Challenge:	Social media is an easy-to-access platform providing timely updates about societal trends and events.
Approach:	They propose a framework to extract epidemic-related events from social media posts to provide early warnings.
Outcome:	The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably.

Copied to clipboard

Hui Gao, Jing Zhang, Peng Zhang, Chang Yang

Socially Aware Bias Measurements for Hindi Language Representations (2022.naacl-main)

Challenge:	Idioms condense complex semantics into fixed phrases, making idiom comprehension a test of metaphor competence.
Approach:	They propose a method to evaluate the metaphor competence of LLMs for the idiom understanding task: the Consistency Rating of Semantic Transparency (CR-ST).
Outcome:	The proposed method assesses the difficulty of understanding idioms through two dimensions: overall semantic transparency and constituent semantic transparency, aiming to gauge LLMs’ mastery of metaphor competence.

Copied to clipboard

Vijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang

Representation Learning

Challenge:	Language representations are an efficient tool used across NLP, but they are strife with encoded societal biases.
Approach:	They investigate the encoded biases in Hindi language representations based on cultural and historical contexts . they emphasize the necessity of social-awareness along with linguistic and grammatical artefacts when modeling language representation .
Outcome:	The proposed model reflects the cultural and cultural diversity of the region in which it is used . the model is based on the language and culture of the language being used based upon the study .

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)

Copied to clipboard

Di Wu, Jia-Chen Gu, Fan Yin, Nanyun Peng, Kai-Wei Chang

Information Retrieval

Challenge:	Existing studies show that RALMs generate baseless information or contradicts with the retrieved context.
Approach:	They propose a lightweight monitor that leverages fine-grained decoding dynamics to synchronously detect unfaithful sentences.
Outcome:	Empirical results show that SynCheck outperforms baseline faithfulness detection and FOD outperformed traditional strategies in terms of faithfulness.

The Woman Worked as a Babysitter: On Biases in Language Generation (D19-1)

Copied to clipboard

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng

Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety (2025.findings-naacl)

Challenge:	a systematic study of biases in natural language generation (NLG) is presented . a study of language models in NLG is conducted by examining language models.
Approach:	They propose a systematic study of biases in natural language generation by analyzing text generated from prompts that contain mentions of different demographic groups.
Outcome:	The proposed method reveals biases in natural language generation (NLG) by analyzing text generated from demographic prompts.

Copied to clipboard

Yiwei Wang, Muhao Chen, Nanyun Peng, Kai-Wei Chang

Transferring General Multimodal Pretrained Models to Text Recognition (2023.findings-acl)

Challenge:	Previous research on jailbreak attacks has focused on optimizing the adversarial snippet content injected into input prompts to expose LLM security vulnerabilities.
Approach:	They propose to use a simple adversarial snippet at the beginning of output to expose LLM security vulnerabilities.
Outcome:	The proposed approach exposes LLM security vulnerabilities much faster than input suffix attacks or prompt-based output jailbreaks.

Copied to clipboard

Junyang Lin, Xuancheng Ren, Yichang Zhang, Gao Liu, Peng Wang, An Yang, Chang Zhou

Improving Event Definition Following For Zero-Shot Event Detection (2024.acl-long)

Challenge:	Existing methods for text recognition rely on large-scale pretraining on human-annotated or synthetic data.
Approach:	They propose a method to transfer multimodal pretrained models to text recognition using image captioning.
Outcome:	The proposed method outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark.

Copied to clipboard

Zefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng

Query-aware Multi-modal based Ranking Relevance in Video Search (2023.emnlp-industry)

Challenge:	Existing approaches on zero-shot event detection train models on datasets annotated with known event types and prompt them with unseen event definitions.
Approach:	They propose to train models to better follow event definitions by using an automatic generated Diverse Event Definition dataset.
Outcome:	The proposed model outperforms existing models on three open benchmarks on zero-shot event detection.

Copied to clipboard

Chengcan Ye, Ting Peng, Tim Chang, Zhiyi Zhou, Feng Wang