Papers by Muhao Chen

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations (2025.findings-naacl)

Challenge:	Existing work only encodes entity types and textual context within individual instances, which limits the performance of sentence-level relation extraction (RE).
Approach:	They propose a module that aggregates the features from sentences to learn global representations of properties and augments local features within individual sentences.
Outcome:	The proposed module can learn global representations of properties from sentences and augment local features within individual sentences.

Copied to clipboard

Wenjie Jacky Mo, Jiashu Xu, Qin Liu, Jiongxiao Wang, Jun Yan, Hadi Askari, Chaowei Xiao, Muhao Chen

Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction? (2023.acl-long)

Challenge:	Existing studies on backdoor defense have focused on training phase, overlooking critical aspect of testing time defense.
Approach:	They propose to use demonstrations as a defense mechanism against backdoor attacks in black-box LLMs.
Outcome:	The proposed method outperforms existing defense baselines across most evaluation scenarios.

Copied to clipboard

Jiashu Xu, Mingyu Derek Ma, Muhao Chen

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection (2025.acl-long)

Challenge:	Existing approaches to biomedical relation extraction (RE) are limited due to the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels.
Approach:	They propose a method which converts biomedical relation extraction (RE) as natural language inference formulation through indirect supervision.
Outcome:	Extensive experiments on three widely-used biomedical RE benchmarks show that indirect supervision improves biomedically relation extraction even when a domain gap exists.

Copied to clipboard

Weidi Luo, Shenghong Dai, Xiaogeng Liu, Suman Banerjee, Huan Sun, Muhao Chen, Chaowei Xiao

Unified Semantic Typing with Meaningful Label Inference (2022.naacl-main)

Challenge:	Existing defense agencies fail to adaptively and effectively mitigate these risks.
Approach:	They propose a lifelong agent guardrail that enhances LLM agent safety by enabling adaptive safety check generation, effective safety check optimization, and tool compatibility & flexibility.
Outcome:	The proposed agent guardrail achieves strong performance against task-specific and systemic risks and is transferable across different LLM agents’ tasks.

Copied to clipboard

James Y. Huang, Bangzheng Li, Jiashu Xu, Muhao Chen

Knowing the No-match: Entity Alignment with Dangling Cases (2021.acl-long)

Challenge:	Semantic typing aims at classifying tokens into semantic categories such as relations, entity types, and event types.
Approach:	They propose a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space.
Outcome:	The proposed framework achieves strong performance across three semantic typing tasks.

Copied to clipboard

Zequn Sun, Muhao Chen, Wei Hu

Structured Data in NLP

Challenge:	Existing approaches to find entities that cannot find alignment across knowledge graphs (KGs) despite their importance, knowledge graph is expensive and suffers from incompleteness.
Approach:	They propose a framework for entity alignment and dangling entity detection that can be used to abstain from predicting alignment for detected dangle entities.
Outcome:	The proposed framework can abstain from predicting alignment for detected dangling entities.

Red Teaming Language Models for Processing Contradictory Dialogues (2024.emnlp-main)

Copied to clipboard

Xiaofei Wen, Bangzheng Li, Tenghao Huang, Muhao Chen

Dialogue Systems & Conversational Agents

Challenge:	a recent study shows that language models are prone to self-contradiction during dialogues.
Approach:	They propose a red teaming framework that detects and attempts to explain dialogues, then modifies existing contradictory content using the explanation.
Outcome:	The proposed task improves the ability to detect contradictory dialogues and provides valid explanations.

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen

Information Retrieval

Challenge:	Retrieval-augmented generation (RAG) improves large language models by incorporating non-parametric knowledge through evidence retrieved from external sources.
Approach:	They propose a training-free evidence compression technique that makes retrieved evidence more familiar to the target model while seamlessly integrating parametric knowledge from the model.
Outcome:	The proposed technique outperforms the most recent evidence compression baselines across open-domain QA datasets while achieving high compression rates.

Are All Steps Equally Important? Benchmarking Essentiality Detection in Event Processes (2023.emnlp-main)

Copied to clipboard

Haoyu Wang, Hongming Zhang, Yueguan Wang, Yuqian Deng, Muhao Chen, Dan Roth

Commonsense Reasoning

Challenge:	Existing models of event processing do not understand the essentiality of step events towards a goal event.
Approach:	They propose to deconstruct a goal event into a discrete representation of finer-grained (step) events, which are not equally important to the goal.
Outcome:	The proposed model can understand the essentiality of different step events towards a goal event.

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs (2026.acl-long)

Copied to clipboard

Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen

Programming Languages in NLP

Challenge:	Existing red-teaming approaches for code generation rely on extensive human effort and are prone to generating malicious code under adversarial environments.
Approach:	They propose a red-teaming agent that engages victim models in multi-turn conversations to elicit vulnerable code.
Outcome:	Experiments show that RedCoder outperforms red-teaming methods in inducing vulnerabilities in code generation.

HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning (2021.findings-emnlp)

Copied to clipboard

Mingyu Derek Ma, Muhao Chen, Te-Lin Wu, Nanyun Peng

Representation Learning

Challenge:	Existing taxonomies have limited coverage due to expensive manual curation process.
Approach:	They propose an algorithm that expands existing taxonomies to preserve their structure in a more expressive hyperbolic embedding space and learns to represent concepts and their relations with a hyperbolical Graph Neural Network.
Outcome:	The proposed algorithm outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking (2024.findings-naacl)

Copied to clipboard

Nan Xu, Fei Wang, Ben Zhou, Bangzheng Li, Chaowei Xiao, Muhao Chen

Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning (2022.naacl-main)

Challenge:	Large language models (LLMs) have demonstrated increasing power, but they also have vulnerabilities.
Approach:	They propose a black-box attack that targets the cognitive structure and processes of large language models (LLMs) they propose defending cognitive overload attacks from three perspectives.
Outcome:	The proposed attack is a black-box attack with no need for knowledge of model architecture or access to model weights.

Copied to clipboard

Fei Wang, Zhewei Xu, Pedro Szekely, Muhao Chen

Primacy Effect of ChatGPT (2023.emnlp-main)

Challenge:	Controlled table-to-text generation is a new approach to generate textual descriptions for highlighted subparts of a table.
Approach:	They propose an equivariance learning framework which encodes tables with a structure-aware self-attention mechanism and a positional encoding mechanism to preserve relative position of tokens in the same cell.
Outcome:	The proposed framework is free to be plugged into existing table-to-text generation models and has improved T5-based models to offer better performance on ToTTo and HiTab.

Copied to clipboard

Yiwei Wang, Yujun Cai, Muhao Chen, Yuxuan Liang, Bryan Hooi

Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation (2023.findings-acl)

Challenge:	Existing machine learning models may lead to poor performance in discriminative natural language understanding tasks.
Approach:	They propose to use ChatGPT to query large amounts of human-written text to find the answer to a question.
Outcome:	The proposed model has a high chance to select labels at earlier positions as the answer.

Copied to clipboard

Xinze Li, Yixin Cao, Muhao Chen, Aixin Sun

Linguistics & Cognitive NLP

Challenge:	Existing work assumes that events are sequentially arranged in a script, while this assumption leads to linear generation that is far from sufficient for comprehensively acquiring the representation about how events are organized towards a task goal.
Approach:	They propose to extend goal-oriented Script Generation task from the perspective of cognitive theory by incorporating subgoals into hierarchical script generation.
Outcome:	The proposed task is based on a new dataset and human evaluation metrics.

Table-based Fact Verification With Salience-aware Learning (2021.findings-emnlp)

Copied to clipboard

Fei Wang, Kexuan Sun, Jay Pujara, Pedro Szekely, Muhao Chen

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models (2024.naacl-long)

Challenge:	Existing methods for fact verification use tabular data with tokens, but training requires labeled training data.
Approach:	They propose a system that identifies token-level salience in the statement with probing-based saliency estimation.
Outcome:	The proposed system improves on TabFact benchmark by replacing non-salient terms with tokens.

Copied to clipboard

Jiashu Xu, Mingyu Ma, Fei Wang, Chaowei Xiao, Muhao Chen

A Causal View of Entity Bias in (Large) Language Models (2023.findings-emnlp)

Challenge:	et al., 2021) show that instruction models can be trained on crowdsourced datasets with task instructions to achieve superior performance.
Approach:	They examine security concerns of emergent instruction tuning paradigm that models are trained on crowdsourced datasets with task instructions to achieve superior performance.
Outcome:	The proposed model can achieve 90% success rate across four commonly used datasets.

Copied to clipboard

Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, Muhao Chen

From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning (2025.naacl-long)

Challenge:	Entity bias affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions.
Approach:	They propose a structured causal model whose parameters are easier to estimate . they propose to perturb the original entity with neighboring entities .
Outcome:	The proposed model reduces biasing information pertaining to the original entity while still preserving sufficient semantic information from similar entities.

Copied to clipboard

Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen

Low-Resource NLP

Challenge:	Motivated by in-context learning capabilities of Large Language Models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as demonstrations.
Approach:	They conduct systematic and principled evaluation of multimodal ICL for models of different scales on a broad spectrum of new yet critical tasks.
Outcome:	The proposed model performance improves on a broad spectrum of new yet critical tasks.

An Improved Baseline for Sentence-level Relation Extraction (2022.aacl-short)

Copied to clipboard

Wenxuan Zhou, Muhao Chen

Salience-Aware Event Chain Modeling for Narrative Understanding (2021.emnlp-main)

Challenge:	Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence.
Approach:	They propose to improve sentence-level relation extraction by adding entity representations with typed markers to the model.
Outcome:	The proposed model outperforms existing methods on entity representation and noisy labels on TACRED dataset.

Copied to clipboard

Xiyang Zhang, Muhao Chen, Jonathan May

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails (2025.findings-acl)

Challenge:	Storytelling is the communication of interesting and related events that form a concrete process.
Approach:	They propose methods for extracting the principal chain from natural language text . they filter away non-salient events and supportive sentences to isolate them . authors propose novel methods for predicting and answering events from text based on event-based temporal question answering .
Outcome:	The proposed method improves narrative prediction and event-based temporal question answering tasks.

Copied to clipboard

Xiaofei Wen, Wenxuan Zhou, Wenjie Jacky Mo, Muhao Chen

Text Classification

Challenge:	Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety violations.
Approach:	They propose a critique-augmented guardrail model that distills knowledge from high-capacity LLMs by generating structured critiques alongside safety labels.
Outcome:	The proposed model outperforms existing guardrail models on multiple safety benchmarks and achieves the highest average F1 and AUPRC.

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (2026.findings-acl)

Copied to clipboard

Qin Liu, Wenxuan Zhou, Nan Xu, James Y. Huang, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen

Are Large Language Models Capable of Generating Human-Level Narratives? (2024.emnlp-main)

Challenge:	Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios.
Approach:	They propose a test-time scaling framework based on meta-thoughts to improve performance . meta-thinkts are adaptive thinking strategies tailored to a given task .
Outcome:	Experimental results show that MetaScale outperforms standard inference approaches . it can scale more effectively with increasing sampling budgets and produces more structured responses .

Copied to clipboard

Yufei Tian, Tenghao Huang, Miri Liu, Derek Jiang, Alexander Spangher, Muhao Chen, Jonathan May, Nanyun Peng

Event-Centric Natural Language Processing (2021.acl-tutorials)

Challenge:	a recent HCI study has pointed to gaps in machine storytelling ability at the global level . authors show that LLMs have less suspense and less tension than human stories .
Approach:	They propose a computational framework to analyze narratives through three discourse-level aspects.
Outcome:	The proposed framework analyzes narratives through three discourse-level aspects . it shows that LLMs fall short of human abilities in discourse understanding .

Copied to clipboard

Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown, Dan Roth

Challenge:	This tutorial will provide an introduction to various methods for automating the extraction, conceptualization and prediction of events and their relations.
Approach:	This tutorial will provide an introduction to various methods for automating events and their relations, and a wide range of NLU and commonsense understanding tasks.
Outcome:	This tutorial will provide an introduction to various methods for automating extraction, conceptualization and prediction of events and their relations, and a wide range of NLU and commonsense understanding tasks.

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors (2024.naacl-long)

Copied to clipboard

Victoria Graf, Qin Liu, Muhao Chen

Dangling-Aware Entity Alignment with Mixed High-Order Proximities (2022.findings-naacl)

Challenge:	Existing defense mechanisms assume that only one type of trigger is adopted by the attacker, while defending against multiple simultaneous and independent trigger types necessitates general defense frameworks.
Approach:	They propose a framework that uses a mixture of experts as a trigger-only ensemble to defend against multiple trigger types.
Outcome:	The proposed framework defends against multiple trigger types in a single ensemble and in combination of models.

Copied to clipboard

Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen

Structured Data in NLP

Challenge:	Existing methods for dangling-aware entity alignment are underexplored but important problem.
Approach:	They propose a framework that uses high-order proximities to detect dangling entities and align matchable entities.
Outcome:	The proposed framework detects dangling entities and aligns matchable entities better than existing methods.

Multi-hop Evidence Retrieval for Cross-document Relation Extraction (2023.findings-acl)

Copied to clipboard

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis (2022.naacl-main)

Challenge:	Relation Extraction (RE) is a task that seeks to identify the relation of entities described according to some context.
Approach:	They propose a multi-hop evidence retrieval method based on evidence path mining and ranking to support cross-document relation extraction.
Outcome:	The proposed method acquires cross-document evidence and boosts performance in both closed and open environments.

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE (2024.naacl-long)

Challenge:	Existing studies rely on entity information for sentence-level relation extraction (RE) but this can leak superficial and spurious clues of relations.
Approach:	They propose to use entity mentions to extract relations from textual context . they use a causal graph to model dependencies between variables in RE models .
Outcome:	The proposed method yields significant gains on both effectiveness and generalization for RE.

Copied to clipboard

Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction (2023.acl-long)

Challenge:	Existing backdoor defense methods focus on specific triggers, leaving a universal defense unexplored.
Approach:	They propose an ensemble-based backdoor defense framework that denies backdoor attacks by capturing backdoor shortcuts and preventing learning them.
Outcome:	The proposed framework significantly improves defense performance against backdoor attacks . it is also effective under a more challenging but practical setting .

Copied to clipboard

Wenxuan Zhou, Sheng Zhang, Tristan Naumann, Muhao Chen, Hoifung Poon

VIPHY: Probing “Visible” Physical Commonsense Knowledge (2023.findings-emnlp)

Challenge:	Relation extraction (RE) has been challenging in low-resource domains and with limited resources.
Approach:	They propose to pretrain and finetune the RE model using consistent objectives of contrastive learning.
Outcome:	The proposed method outperforms PLM-based RE classifier on two document-level RE datasets.

Copied to clipboard

Shikhar Singh, Ehsan Qasemi, Muhao Chen

Prix-LM: Pretraining for Multilingual Knowledge Base Construction (2022.acl-long)

Challenge:	Existing studies have demonstrated that vision-language models can retain and generalize knowledge, but they do not measure their ability to retain it.
Approach:	They build an automatic pipeline to derive a knowledge resource for calibrating and probing vision-language models.
Outcome:	The proposed model outperforms the pretrained model on size and spatial tasks.

Copied to clipboard

Wenxuan Zhou, Fangyu Liu, Ivan Vulić, Nigel Collier, Muhao Chen

Enhancing LLM Capabilities Beyond Scaling Up (2024.emnlp-tutorials)

Challenge:	Existing methods to build and enrich multilingual knowledge bases have not been successful . knowledge expressed in different languages may be complementary and unequally distributed .
Approach:	They propose a model that integrates useful multilingual and KB-based factual knowledge into a single model.
Outcome:	The proposed model can provide richer combined knowledge than monolingual KBs.

Copied to clipboard

Wenpeng Yin, Muhao Chen, Rui Zhang, Ben Zhou, Fei Wang, Dan Roth

PInKS: Preconditioned Commonsense Inference with Minimal Supervision (2022.aacl-main)

Challenge:	general-purpose large language models (LLMs) are expanding in scale and access to unpublic training data.
Approach:	This tutorial aims to examine the capabilities of general-purpose large language models . authors discuss adaptation of LLMs to address conflicts, defense against attacks .
Outcome:	This tutorial aims to examine the evolution of general-purpose large language models (LLMs) the authors argue that the evolution is dependent on the availability of training data and the scale of the models.

Copied to clipboard

Ehsan Qasemi, Piyush Khanna, Qiang Ning, Muhao Chen

Code Execution as Grounded Supervision for LLM Reasoning (2025.emnlp-main)

Challenge:	Existing models for reasoning with preconditions lack data on the problem and lack of support for such reasoning.
Approach:	They propose to improve the model for reasoning with preconditions through minimum supervision by PAC-Bayesian informativeness analysis and precision measures.
Outcome:	The proposed model improves on benchmarks focused on reasoning with the preconditions of commonsense knowledge (up to 40% Macro-F1 scores) it also improves inferences on PAC-Bayesian informativeness analysis, precision measures, and ablation studies.

Copied to clipboard

Dongwon Jung, Wenxuan Zhou, Muhao Chen

mDPO: Conditional Preference Optimization for Multimodal Large Language Models (2024.emnlp-main)

Challenge:	Existing methods for generating high-quality CoT data rely on costly human annotations and error-prone CoT.
Approach:	They propose a method that extracts verifiable, step-by-step reasoning traces from code execution and transforms them into a natural language CoT reasoning.
Outcome:	The proposed method produces highly accurate reasoning data and reduces overall token length during inference by reducing meaningless repetition and overthinking.

Copied to clipboard

Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen

Multimodality

Challenge:	Recent studies have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement.
Approach:	They propose a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference.
Outcome:	The proposed method significantly improves performance on two multimodal LLMs of different sizes and three widely used benchmarks.

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference (2022.tacl-1)

Copied to clipboard

Bangzheng Li, Wenpeng Yin, Muhao Chen

Monotonic Paraphrasing Improves Generalization of Language Model Prompting (2024.findings-emnlp)

Challenge:	Existing methods for ultra-fine entity typing fail to capture type semantics because of the large number of types and the scarcity of data per type.
Approach:	They propose a method that formulates entity typing as a natural language inference problem . they use indirect supervision from NLI to infer type information as textual hypotheses .
Outcome:	The proposed method achieves state-of-the-art performance on the ultra-fine entity typing task with limited training data.

Copied to clipboard

Qin Liu, Fei Wang, Nan Xu, Tianyi Yan, Tao Meng, Muhao Chen

Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning (2021.naacl-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in zero-shot decision making and instruction following.
Approach:	They propose an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt rewriting, and a target LM that constrains the generation for lower perxity.
Outcome:	The proposed method can efficiently paraphrase the original prompt without altering its semantic meaning while decreasing the perplexity of each generation as calculated by the target LM.

Copied to clipboard

Xuelu Chen, Michael Boratko, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li, Andrew McCallum

GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)

Challenge:	Existing methods to generalize knowledge bases model triple-level uncertainty . Existing models only model triple level uncertainty, and reasoning results lack global consistency.
Approach:	They propose a method to embed knowledge graphs with calibrated probabilistic semantics . they model each entity as a box and relations between two entities as affine transforms based on affinity transforms.
Outcome:	Experiments show that the proposed method outperforms baseline methods on confidence prediction and fact ranking.

Copied to clipboard

Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu

Green & Sustainable NLP

Challenge:	Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process .
Approach:	They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories.
Outcome:	The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation.

Joint Constrained Learning for Event-Event Relation Extraction (2020.emnlp-main)

Copied to clipboard

Haoyu Wang, Muhao Chen, Hongming Zhang, Dan Roth

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities (2024.naacl-long)

Challenge:	Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.
Approach:	They propose a joint constrained learning framework that enforces logical constraints within and across multiple temporal and subevent relations of events by converting constraints into differentiable learning objectives.
Outcome:	The proposed framework outperforms SOTA methods on benchmarks for temporal relation extraction and event hierarchy construction.

Copied to clipboard

Lingbo Mo, Boshi Wang, Muhao Chen, Huan Sun

Do Language Models Perform Generalizable Commonsense Inference? (2021.findings-acl)

Challenge:	Rapid progress in open-source Large Language Models (LLMs) is driving AI development, but lacks sufficient trustworthiness to detect and mitigate adversarial demonstrations.
Approach:	They propose an extended Chain of Utterances-based (CoU) prompting strategy to attack open-source LLMs.
Outcome:	The proposed attack strategy is based on malicious demonstrations and toxicity tests on open-source models.

Copied to clipboard

Peifeng Wang, Filip Ilievski, Muhao Chen, Xiang Ren

Summarization as Indirect Supervision for Relation Extraction (2022.findings-emnlp)

Challenge:	Recent work has applied pretrained language models to populate commonsense knowledge graphs (CKGs) but there is a lack of understanding on their generalization to multiple CKGs, unseen relations, and novel entities.
Approach:	They analyze the ability of pretrained language models to perform generalizable commonsense inference in terms of knowledge capacity, transferability and induction.
Outcome:	The proposed models can adapt to different schemas defined by multiple CKGs but fail to generalize to new relations.

Copied to clipboard

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen

Learning Constraints and Descriptive Segmentation for Subevent Detection (2021.emnlp-main)

Challenge:	Relation extraction (RE) models rely on training data with expensive annotations . et al., 2018; Zhao e.t al, 2018) .
Approach:	They propose a method that converts RE into a summarization formulation by using constraint decoding techniques.
Outcome:	The proposed method improves relation extraction models with high-resource and high-contrast inferences.

Copied to clipboard

Haoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth

Challenge:	Event mentions in text correspond to real-world events of varying degrees of granularity . task of subevent detection aims to resolve this granulem issue by recognizing membership of events .
Approach:	They propose a task of event-based text segmentation as an auxiliary task to improve learning for subevent detection.
Outcome:	The proposed method outperforms baseline methods on subevent detection, HiEve and IC datasets while achieving decent performance on EventSeg prediction.

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing (2025.findings-naacl)

Copied to clipboard

Hadi Askari, Anshuman Chhabra, Muhao Chen, Prasant Mohapatra

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have achieved state-of-the-art performance at zero-shot summarization of abstractive summaries for given articles, but little is known about their robustness at this task.
Approach:	They propose a strategy that uses the most relevant sentences to generate an ideal summary and then paraphrases them to obtain a minimally perturbed dataset.
Outcome:	The proposed approach can be used to measure the robustness of LLMs as summarizers on a minimally perturbed dataset.

Copied to clipboard

Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin

Planning and Editing What You Retrieve for Enhanced Tool Learning (2024.findings-naacl)

Challenge:	Recent studies have focused on few-shot and zero-shot learning, but label occurrences vary widely . authors propose a new classification challenge that can be used to manage labels across the full frequency spectrum .
Approach:	They propose a new classification challenge that allows for label co-occurrences without predefined limits.
Outcome:	The proposed system can handle freq-shot, few-shot and zero-shot labels without limits.

Copied to clipboard

Tenghao Huang, Dongwon Jung, Vaibhav Kumar, Mohammad Kachuee, Xiang Li, Puyang Xu, Muhao Chen

Information Retrieval

Challenge:	Existing methods for integrating external tools with Large Language Models fall short on effectively shortlisting relevant tools.
Approach:	They propose a plan-and-retrieve and edit-and ground paradigms for LLMs that decompose complex queries into actionable tasks.
Outcome:	The proposed paradigms significantly improve recall and NDCG in tool retrieval tasks, surpassing current state-of-the-art models.

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation (2025.emnlp-main)

Copied to clipboard

Hongxiang Zhang, Hao Chen, Muhao Chen, Tianyi Zhang

Contrastive Instruction Tuning (2024.findings-acl)

Challenge:	Recent decoding methods improve the factuality of large language models (LLMs) by refining how the next token is selected during generation.
Approach:	They propose a decoding strategy that actively decides when to apply contrasting layers during generation by casting decoding as a sequential decision-making problem.
Outcome:	The proposed method surpasses state-of-the-art methods across five benchmarks and mitigates hallucinations in diverse generation scenarios.

Copied to clipboard

Tianyi Yan, Fei Wang, James Y. Huang, Wenxuan Zhou, Fan Yin, Aram Galstyan, Wenpeng Yin, Muhao Chen

New Frontiers of Information Extraction (2022.naacl-tutorials)

Challenge:	Current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles.
Approach:	They propose a method which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarities between semantically different ones.
Outcome:	Experiments on the PromptBench benchmark show that Contrastive Instruction Tuning improves LLMs’ robustness to unseen instructions with variations across character, word, sentence, and semantic levels by +2.5% in accuracy.

Copied to clipboard

Muhao Chen, Lifu Huang, Manling Li, Ben Zhou, Heng Ji, Dan Roth

Answer Consolidation: Formulation and Benchmarking (2022.naacl-main)

Challenge:	Information extraction (IE) is the process of automatically extracting structural information from unstructured or semi-structured data.
Approach:	This tutorial will provide an introduction to recent advances in IE by answering several important research questions.
Outcome:	The tutorial will address several important research questions and outline directions for further investigation.

Copied to clipboard

Wenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, Muhao Chen

Natural Language Interfaces

Challenge:	Current question answering systems assume each question to have one correct answer.
Approach:	They propose a problem where answers are partitioned into multiple groups . they construct a comprehensive and non-redundant set of answers by picking one answer from each group .
Outcome:	The proposed model performs better than previous models, but it needs further improvements.

Examining Gender Bias in Languages with Grammatical Gender (D19-1)

Copied to clipboard

Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan-Hao Huang, Muhao Chen, Ryan Cotterell, Kai-Wei Chang

Multilinguality

Challenge:	Existing studies on gender bias in word embeddings focus on English . however, these studies cannot be extended to languages with morphological agreement on gender .
Approach:	They propose new metrics to evaluate gender bias in word embeddings of English and Spanish . they extend existing approaches to mitigate gender bias while preserving original embeddables .
Outcome:	The proposed methods reduce gender bias while preserving the original embeddings.

PaCo: Preconditions Attributed to Commonsense Knowledge (2022.findings-emnlp)

Copied to clipboard

Ehsan Qasemi, Filip Ilievski, Muhao Chen, Pedro Szekely

Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (2023.emnlp-main)

Challenge:	Existing language models can reason with circumstantial preconditions of commonsense knowledge, but they do not understand the circumstancial precondition.
Approach:	They propose to use a dataset to examine the ability of existing language models to understand circumstantial preconditions to improve their reasoning with commonsense knowledge.
Outcome:	The proposed task shows that human reasoning with preconditions is an open challenge.

Copied to clipboard

James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang, Muhao Chen, Dong Yu

Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality (2023.acl-short)

Challenge:	Existing approaches to learn sentence embeddings do not capture the semantic similarity of sentences.
Approach:	They propose a framework that integrates compositional sentence operations into the embedding space and optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddables.
Outcome:	The proposed framework improves the interpretability of sentence embeddings on four textual generation tasks while maintaining strong performance on traditional semantic similarity tasks.

Copied to clipboard

Tanay Dixit, Fei Wang, Muhao Chen

Parameter-Efficient Tuning with Special Token Adaptation (2023.eacl-main)

Challenge:	Recent studies have shown that most abstractive summarization models are unfaithful and suffer from a wide range of hallucination.
Approach:	They propose a candidate summary generation and ranking technique to improve summary factuality without sacrificing quality.
Outcome:	The proposed method shows that the model trained using the proposed method improves on factuality and similarity-based metrics without conflicting with the model.

Copied to clipboard

Xiaocong Yang, James Y. Huang, Wenxuan Zhou, Muhao Chen

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models (2024.acl-long)

Challenge:	a recent study shows that parameter-efficient tuning is a challenge for multitask deployments.
Approach:	They propose a parameter-efficient tuning technique that only updates a small subset of parameters when adapting a pretrained model to downstream tasks.
Outcome:	The proposed method achieves comparable performance to fine-tuning in natural language understanding tasks including text classification and NER with only 0.029% of parameters trained.

Copied to clipboard

Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing (2022.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have significantly enhanced the capabilities in natural language processing.
Approach:	They propose a method to poison large language models by using annotators to rank a set of collected responses to generate longer tokens.
Outcome:	The proposed method can generate longer tokens without harming the original safety alignment performance.

Copied to clipboard

Nan Xu, Fei Wang, Bangzheng Li, Mingtao Dong, Muhao Chen

Retrofitting Contextualized Word Embeddings with Paraphrases (D19-1)

Challenge:	Existing entity typing models are subject to spurious correlations due to shortcuts and biased training.
Approach:	They propose a method to augment existing model biases by combining spurious correlations with debiasedcounterparts to improve generalization.
Outcome:	The proposed method improves generalization of different entity typing models on the original and debiased test sets.

Copied to clipboard

Weijia Shi, Muhao Chen, Pei Zhou, Kai-Wei Chang

Representation Learning

Challenge:	Contextualized word embeddings can be useful for downstream applications, but they can be over-sensitive to contexts.
Approach:	They propose a method to retrofit contextualized word embeddings with paraphrases to minimize the variance of word representations on paraphrased contexts.
Outcome:	The proposed method improves on sentence classification and inference tasks.

GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding (2023.emnlp-main)

Copied to clipboard

Zekun Li, Wenxuan Zhou, Yao-Yi Chiang, Muhao Chen

Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning (2024.findings-naacl)

Challenge:	Pretrained language models do not utilize valuable geospatial information in large databases, e.g., OpenStreetMap.
Approach:	They propose a geospatially grounded language model that connects linguistic and geospheric contexts.
Outcome:	The proposed model bridges the gap between natural language processing and geospatial sciences.

Copied to clipboard

Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, Muhao Chen

Analogous Process Structure Induction for Sub-event Sequence Prediction (2020.emnlp-main)

Challenge:	Event temporal reasoning aims at identifying the temporal relations between two or more events from narratives.
Approach:	They propose to detect knowledge conflicts in event temporal reasoning using bias indicators such as event relation prior bias, tense bias, narrative bias, and dependency bias.
Outcome:	The proposed method can be applied to Pre-trained Language Models and Large Language Model (LLMs) as additional training data or demonstrations for In- Context Learning.

Copied to clipboard

Hongming Zhang, Muhao Chen, Haoyu Wang, Yangqiu Song, Dan Roth

Challenge:	Existing work on event understanding is focusing on procedural (or horizontal) tasks such as predicting the next event given an observed sequence.
Approach:	They propose an Analogous Process Structure Induction framework which leverages analogies among processes and conceptualization of sub-event instances to predict the whole sub- sequence of previously unseen open-domain processes.
Outcome:	The proposed framework can predict the whole sub-event sequence of previously unseen open-domain processes.

Salience Allocation as Guidance for Abstractive Summarization (2022.emnlp-main)

Copied to clipboard

Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu

Dense Retrieval as Indirect Supervision for Large-space Decision Making (2023.findings-emnlp)

Challenge:	Abstractive summarization models implicitly learn to capture the salient information from scratch.
Approach:	They propose a method that uses salience expectation to guide abstractive summarization by averaging salient content to a fixed threshold.
Outcome:	The proposed method can be easily adapted to documents with various abstractiveness and achieves high performance.

Copied to clipboard

Nan Xu, Fei Wang, Mingtao Dong, Muhao Chen

Information Retrieval

Challenge:	Dense Decision Retrieval (DDR) is a learning-to-retrieve task for discriminative natural language understanding (NLU) tasks with large label spaces.
Approach:	They propose a novel approach to learning large-space discriminative NLU tasks as a learning-to-retrieve task by adopting a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus.
Outcome:	The proposed approach outperforms baselines greatly on multi-label classification tasks, 1.17% in F1 score ultra-fine entity typing, and 1.26% in accuracy on three few-shot intent classification tasks on average.

Contrastive Out-of-Distribution Detection for Pretrained Transformers (2021.emnlp-main)

Copied to clipboard

Wenxuan Zhou, Fangyu Liu, Muhao Chen

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization (2025.findings-emnlp)

Challenge:	Pretrained Transformers achieve remarkable performance when training and test data are from the same distribution, but in real-world scenarios, out-of-distribution instances can cause semantic shift problems.
Approach:	They propose to fine-tune the Transformers with a contrastive loss, which improves the compactness of representations, and to use the Mahalanobis distance in the model's penultimate layer to detect OOD instances.
Outcome:	The proposed method outperforms baselines in the real-world and achieves near-perfect OOD detection performance.

Copied to clipboard

Shuyang Hao, Yiwei Wang, Bryan Hooi, Jun Liu, Muhao Chen, Zi Huang, Yujun Cai

Affective and Dynamic Beam Search for Story Generation (2023.findings-emnlp)

Challenge:	HKVE selectively accepts gradient optimization results based on the distribution of attention scores across different layers, ensuring that every optimization step positively contributes to the attack.
Approach:	They propose a framework that selectively accepts gradient optimization results based on the distribution of attention scores across different layers and selectively takes them into account when calculating the attack success rate.
Outcome:	The proposed framework outperforms existing methods by achieving success rates of 75.08% on MiniGPT4, 85.84% on LLaVA and 81.00% on Qwen-VL.

Copied to clipboard

Tenghao Huang, Ehsan Qasemi, Bangzheng Li, He Wang, Faeze Brahman, Muhao Chen, Snigdha Chaturvedi

Rethinking Tabular Data Understanding with Large Language Models (2024.naacl-long)

Challenge:	AffGen introduces ‘intriguing twists’ in narratives by employing two novel techniques—Dynamic Beam Sizing and Affective Reranking.
Approach:	They propose to use dynamic beam sizing and affective reranking to generate interesting stories using two novel techniques.
Outcome:	The proposed method outperforms baseline models in generating affectively charged and interesting narratives.

Copied to clipboard

Tianyang Liu, Fei Wang, Muhao Chen

Sharpness-Aware Minimization with Dynamic Reweighting (2022.findings-emnlp)

Challenge:	Large Language Models (LLMs) are capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area.
Approach:	They propose a method for table structure normalization to improve model performance . they propose aggregation of multiple reasoning pathways to improve performance based on textual and symbolic reasoning.
Outcome:	The proposed method improves performance on symbolic reasoning tasks with textual reasoning slightly outperforming symbolic reasoning on tables.

Copied to clipboard

Wenxuan Zhou, Fangyu Liu, Huan Zhang, Muhao Chen

Robust Natural Language Understanding with Residual Attention Debiasing (2023.findings-acl)

Challenge:	Deep neural networks are often overparameterized and can overfit training data.
Approach:	They propose an adversarial weight minimization algorithm that conducts adversarials and finds a common adversaria per-batch.
Outcome:	The proposed algorithm finds a common adversarial weight perturbation per-batch.

Copied to clipboard

Fei Wang, James Y. Huang, Tianyi Yan, Wenxuan Zhou, Muhao Chen

Instructional Fingerprinting of Large Language Models (2024.naacl-long)

Challenge:	Existing ensemble-based debiasing methods do not address unintended dataset biases . attention plays a crucial role in providing robust prediction in NLU models .
Approach:	They propose an end-to-end debiasing method that mitigates unintended biases from attention.
Outcome:	The proposed method improves the OOD performance of BERT-based models on three benchmarks.

Copied to clipboard

Jiashu Xu, Fei Wang, Mingyu Ma, Pang Wei Koh, Chaowei Xiao, Muhao Chen

R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory (2025.acl-long)

Challenge:	Large language models (LLMs) require considerable cost to train from scratch . fingerprinting is essential to protect intellectual property and to ensure downstream users and developers adhere to their license terms.
Approach:	They propose a method for fingerprinting Large language models that implants a private key into the model to generate specific text when the key is present.
Outcome:	The proposed method prevents publisher overclaim and maintains robustness against fingerprint guessing and parameter-efficient training.

Copied to clipboard

Tenghao Huang, Kinjal Basu, Ibrahim Abdelaziz, Pavan Kapanipathi, Jonathan May, Muhao Chen

Challenge:	Existing methods for web agents struggle with efficient navigation and action execution due to limited visibility and understanding of web structures.
Approach:	They propose a framework that integrates memory-enhanced navigation and reflective learning to improve web agents' performance.
Outcome:	The proposed framework shows significant improvements over existing methods, including 50% reduction in navigation errors and threefold increase in task completion rates.

QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Copied to clipboard

Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou

Explainability & Interpretability in NLP

Challenge:	QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach:	a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome:	QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)

Copied to clipboard

Cheng Wang, Zeming Wei, Qin Liu, Wenxuan Zhou, Muhao Chen

SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation (2022.findings-emnlp)

Challenge:	Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations.
Approach:	They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content.
Outcome:	The proposed methods show that they learn superficial patterns rather than semantic harmfulness.

Copied to clipboard

Zekun Li, Jina Kim, Yao-Yi Chiang, Muhao Chen

Contrastive Bootstrapping for Label Refinement (2023.acl-short)

Challenge:	Named geographic entities are the building blocks of many geographic datasets.
Approach:	They propose a spatial language model that provides a general-purpose geo-entity representation based on neighboring entities in geospatial data.
Outcome:	The proposed model improves on two downstream tasks, showing significant performance improvement compared with existing models that do not use spatial context.

Copied to clipboard

Shudi Hou, Yu Xia, Muhao Chen, Sujian Li

On-the-fly Denoising for Data Augmentation in Natural Language Understanding (2024.findings-eacl)

Challenge:	Existing methods for fine-grained classification categorize texts into coarse-gritty classes, but they are suboptimal in real-world scenarios.
Approach:	They propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages.
Outcome:	The proposed method outperforms the state-of-the-art methods by a large margin on NYT and 20News datasets.

Copied to clipboard

Tianqing Fang, Wenxuan Zhou, Fangyu Liu, Hongming Zhang, Yangqiu Song, Muhao Chen

Low-Resource NLP

Challenge:	Existing methods to improve data augmentation performance may introduce noisy data that impairs training.
Approach:	They propose an on-the-fly denoising technique that learns from soft augmented labels provided by an organic teacher model trained on the cleaner original dataset.
Outcome:	The proposed method improves on text classification and question-answering tasks on general augmentation techniques and prevents overfitting on noisy labels.

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting (2026.acl-short)

Copied to clipboard

Cheng Wang, Qin Liu, Wenxuan Zhou, Muhao Chen

Knowledge Association with Hyperbolic Knowledge Graph Embeddings (2020.emnlp-main)

Challenge:	Excessive exploitation can cause the model to become overconfident in its suboptimal solutions, thereby limiting its capabilities to explore novel reasoning strategies.
Approach:	They propose a method that dynamically down-weights extreme token-level updates via a Gaussian kernel and reduces the instability caused by the trade-off.
Outcome:	The proposed method improves downstream performance across reasoning benchmarks and stabilizes entropy as training progresses.

Copied to clipboard

Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai, Wei Zhang

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

Challenge:	Existing methods for knowledge graphs (KGs) depend on high embedding dimensions and hierarchical structures to achieve expressiveness.
Approach:	They propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a high-dimensional transformation.
Outcome:	Experiments on entity alignment and type inference show the proposed method is effective and efficient.

Copied to clipboard

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

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment (2025.acl-long)

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

Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks (2024.findings-emnlp)

Challenge:	Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model parametric knowledge with non-preferred features is uniformly blocked to all the users.
Approach:	They propose a framework that lets LLMs learn access control over parametric knowledge for users with different credentials via authorization alignment.
Outcome:	Experiments on two application scenarios show that the proposed framework effectively controls the user’s access to parametric knowledge and maintains its general utility.

Copied to clipboard

Terry Tong, Qin Liu, Jiashu Xu, Muhao Chen

Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction (2023.eacl-main)

Challenge:	Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance.
Approach:	They propose a decoding time defense that scales linearly with the input sequence length and reduces the backdoor to as low as 0.35%.
Outcome:	The proposed framework is generalizable, compatible with any trigger in an adversary’s toolbox in a plug-and-play manner.

Copied to clipboard

Haoyu Wang, Hongming Zhang, Yuqian Deng, Jacob Gardner, Dan Roth, Muhao Chen

Cross-lingual Entity Alignment with Incidental Supervision (2021.eacl-main)

Challenge:	Existing models for event temporal relation extraction are based on data-driven machine learning . however, TEMPREL extraction is not accurate under distribution shifts.
Approach:	They propose to conduct counterfactual analysis to attenuate the effects of two types of training biases: the event trigger bias and the frequent label bias.
Outcome:	The proposed model extracts TempRel and timelines more faithfully compared to SOTA methods . it is based on two perspectives: one is to extract genuinely based upon contextual description . the other is to provide proper uncertainty estimation and abstain from extraction when no relation is described in the text .

Copied to clipboard

Muhao Chen, Weijia Shi, Ben Zhou, Dan Roth

Context-faithful Prompting for Large Language Models (2023.findings-emnlp)

Challenge:	Existing methods to match entities in multilingual knowledge graphs are insufficient, resulting in inconsistent seed alignment between KGs.
Approach:	They propose a model that integrates multilingual KGs and monolingual text corpora in a shared embedding scheme and a self-learning based alignment learning process to induce correspondence between entities and lexemes.
Outcome:	The proposed model significantly outperforms state-of-the-art methods on benchmark datasets and significantly outpersts existing methods.

Copied to clipboard

Wenxuan Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen

Indirectly Supervised Natural Language Processing (2023.acl-tutorials)

Challenge:	Large language models encode parametric knowledge about world facts but overly rely on it can cause incorrect predictions in context-sensitive NLP tasks.
Approach:	They propose to use opinion-based prompts and counterfactual demonstrations to improve LLM faithfulness to contexts.
Outcome:	The proposed methods improve faithfulness to contexts using opinion-based prompts and counterfactual demonstrations.

Copied to clipboard

Wenpeng Yin, Muhao Chen, Ben Zhou, Qiang Ning, Kai-Wei Chang, Dan Roth

Challenge:	a tutorial on indirect supervision addresses challenges in ML for NLP . conventional approaches to NLP use taskspecific labeled examples of a large volume . indirect supervision is useful for a wide range of NLP tasks, but it is not enough for decoders .
Approach:	This tutorial aims to address questions about indirect supervision in machine learning . authors discuss indirect supervision from T′ that handles T with outputs spanning from a moderate size to an open space .
Outcome:	This tutorial aims to answer questions about how to provide supervision for ML tasks . it will discuss indirect supervision from T′ that handles T with outputs spanning from a moderate size to an open space .

Learning from Noisy Labels for Entity-Centric Information Extraction (2021.emnlp-main)

Copied to clipboard

Wenxuan Zhou, Muhao Chen

Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer (2020.findings-emnlp)

Challenge:	Recent information extraction approaches can easily overfit noisy labels and suffer from performance degradation.
Approach:	They propose a co-regularization framework for entity-centric information extraction that optimizes neural models with task-specific losses and regularizes them to generate similar predictions based on agreement loss.
Outcome:	The proposed framework is optimized with task-specific losses and generates similar predictions based on agreement loss.

Copied to clipboard

Xuelu Chen, Muhao Chen, Changjun Fan, Ankith Uppunda, Yizhou Sun, Carlo Zaniolo

Combating Security and Privacy Issues in the Era of Large Language Models (2024.naacl-tutorials)

Challenge:	Existing methods for learning missing facts in knowledge graphs are limited by insufficiency of alignment information and inconsistency of described facts.
Approach:	They propose a framework for embedding learning and ensemble knowledge transfer across KGs.
Outcome:	The proposed framework improves state-of-the-art methods on language-specific KGs.

Copied to clipboard

Muhao Chen, Chaowei Xiao, Huan Sun, Lei Li, Leon Derczynski, Anima Anandkumar, Fei Wang

Teaching Language Models To Gather Information Proactively (2025.findings-emnlp)

Challenge:	a tutorial aims to provide a summary of risks and vulnerabilities in large language models . a number of studies have focused on security, privacy and copyright aspects of LLMs .
Approach:	This tutorial seeks to provide a systematic summary of risks and vulnerabilities in large language models . authors will discuss security, privacy and copyright aspects of LLMs .
Outcome:	This tutorial aims to provide a systematic summary of risks and vulnerabilities in large language models . it will also outline emerging challenges in security, privacy and reliability of LLMs .

Copied to clipboard

Tenghao Huang, Sihao Chen, Muhao Chen, Jonathan May, Longqi Yang, Mengting Wan, Pei Zhou