Safe Reasoning

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment [PDF][Website]
Hongjue Zhao*, Haosen Sun*, Jiangtao Kong, Xiaochang Li, Qineng Wang, Liwei Jiang, Qi Zhu, Tarek F. Abdelzaher, Yejin Choi, Manling Li+, Huajie Shao+ (equal advising)
ICLR 2026

LLM AlignmentActivation SteeringFlow MatchingControl TheoryAI Safety

Fairness Failure Modes of Multimodal LLMs [PDF]
Canyu Chen*, Anglin Cai*, Joan Nwatu, Yale Li, Han Liu, Jessica Hullman, Rada Mihalcea, Kathleen McKeown, Manling Li
Preprint, 2026

FairnessMultimodal LLMsBias EvaluationTrustworthy AI

Weak-to-Strong Generalization with Failure Trajectories [PDF]
Ruimeng Ye, Zihan Wang, Yang Xiao, Zinan Ling, Manling Li, Bo Hui
ICLR 2026

Weak-to-Strong GeneralizationScalable OversightAlignmentFailure Trajectories

Your Language Model Secretly Contains Personality Subnetworks [PDF][Code]
Ruimeng Ye, Zihan Wang, Zinan Ling, Yang Xiao, Manling Li, Xiaolong Ma, Bo Hui
ICLR 2026

InterpretabilityPersonality SubnetworksModel EditingLLM Alignment

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents [PDF]
Simon Sinong Zhan, Yao Liu, Philip Wang, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu
2025

Safety EvaluationFormal MethodsEmbodied Agent SafetyTemporal Logic

The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucination [PDF]
Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi Fung, Kathleen McKeown, ChengXiang Zhai, Manling Li, Heng Ji
ACL 2025 Findings

HallucinationKnowledge OvershadowingLLM TruthfulnessHallucination Prediction

ACLED-DS: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World [PDF]
Sina Semnani, Pingyue Zhang, Wanyue Zhai, Haozhuo Li, Ryan Beauchamp, Trey Billing, Katayoun Kishi, Manling Li, Monica Lam
ACL 2025 Findings

Event ExtractionMultilingual DatasetConflict AnalysisInformation Extraction

Chain-of-Experts: Unlocking the Communication Power of MoEs [PDF][Blog][Code][tl;dr]
Zihan Wang, Rui Pan, Jiarui Yao, Róbert Csordás, Linjie Li, Lu Yin, Jiajun Wu, Tong Zhang, Manling Li, Shiwei Liu

Mixture-of-ExpertsSparse ArchitecturesExpert CommunicationLLM Efficiency

LM-Steer: Word Embeddings Are Steers for Language Models [Website][PDF][Code][Live Demo][Slides][Poster]
Chi Han, Jialiang Xu, Manling Li, Yi Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, Heng Ji
ACL 2024
(Outstanding Paper Award at ACL 2024)

LLM SteeringControllable GenerationWord EmbeddingsAlignmentInterpretability

Why Does New Knowledge Create Messy Ripple Effects in LLMs? [PDF]
Jiaxin Qin, Zixuan Zhang, Chi Han, Pengfei Yu, Manling Li, Heng Ji
EMNLP 2024

Knowledge EditingRipple EffectsLLM Knowledge

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders [PDF]
Cheng Li, May Fung, Qingyun Wang, Chi Han, Manling Li, Jindong Wang, Heng Ji
2024

Self-Play TrainingMental Health AILLM Applications

Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate [PDF]
Kyungha Kim*, Sangyun Lee*, Kung-Hsiang Huang*, Hou Pong Chan, Manling Li, Heng Ji
2024

Fact-CheckingFaithful ExplanationsMulti-Agent Debate

InfoPattern: Unveiling Information Propagation Patterns in Social Media [PDF]
Chi Han*, Jialiang Xu*, Manling Li* , Hanning Zhang*, Tarek Abdelzaher, Heng Ji
2023

Information PropagationSocial Media AnalysisComputational Social Science

SmartBook: AI-Assisted Situation Report Generation [PDF]
Revanth Gangi Reddy, Yi Fung, Qi Zeng, Manling Li, Zihan Wang, Paul Sullivan, Heng Ji
2023

Situation Report GenerationAI-Assisted WritingEvent Understanding

Controlling Object Existence Hallucinations in Large Vision Language Models [PDF]
Bohan Zhai, Shijia Yang, Chenfeng Xu, Sheng Shen, Kurt Keutzer, Chunyuan Li, Manling Li
2023

Object HallucinationHallucination MitigationVision-Language Models

Event-centric Multimodal Knowledge Acquisition [PDF]
Manling Li
Thesis Committee: Heng Ji, Jiawei Han, Chengxiang Zhai, Shih-Fu Chang, Kyunghyun Cho
Thesis

Multimodal Knowledge AcquisitionEvent-Centric NLPInformation Extraction

Defining a New NLP Playground [PDF]
Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel R. Tetreault, Eduard H Hovy, Heng Ji
EMNLP 2023 Findings

NLP Research AgendaLarge Language ModelsPosition Paper

ADEPT: A DEbiasing PrompT Framework [PDF] [Code]
Ke Yang^†, Charles Yu, Yi Fung, Manling Li, Heng Ji
AAAI 2023 (^† denotes supervised undergraduate)

DebiasingPrompt TuningFairness in NLP

COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System [PDF] [Code] [Demo] [Video]
Manling Li, Revanth Gangi Reddy, Ziqi Wang, Yi-Shyuan Chiang, Tuan M. Lai, Pengfei Yu, Zixuan Zhang,Heng Ji
ACL'22 Demo

Claim ExtractionMisinformation TrackingNLP System

MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding [PDF] [Data]
Revanth Gangi Reddy^†, Xilin Rui^†, Manling Li, Xudong Lin, Haoyang Wen, Jaemin Cho, Lifu Huang, Mohit Bansal, Avi Sil, Shih-Fu Chang, Alexander Schwing, Heng Ji
AAAI'22

Multimedia Question AnsweringMulti-Hop ReasoningCross-Media Grounding

Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport [PDF] [Data]
Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji and Kathleen McKeown
EMNLP'21

Timeline SummarizationEvent GraphsOptimal Transport

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation [PDF] [Code/Data]
Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, David Liem, Ahmed Elsayed, Martha Palmer, Jasmine Rah, Clare Voss, Cynthia Schneider, Boyan Onyshkevych
NAACL'21: System Demonstrations
(Best Demo Paper Award at NAACL2021)

Knowledge Graph ConstructionDrug RepurposingScientific NLP

RESIN: A Dockerlized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System [PDF] [Code]
Haoyang Wen, Ying Lin, Tuan M. Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi R. Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan W. Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang and Heng Ji
NAACL'21: System Demonstrations

Schema-Guided ExtractionCross-LingualCross-MediaInformation Extraction System

GAIA: A Fine-grained Multimedia Knowledge Extraction System [PDF] [Code] [Video]
Manling Li*, Alireza Zareian*, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare R. Voss, Dan Napierski, Marjorie Freedman
ACL'20: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. pp. 77–86
(Best Demo Paper Award at ACL2020)

Multimedia Knowledge ExtractionKnowledge GraphsFine-Grained Entities

GAIA at SM-KBP 2020 - A Dockerized Multi-media Multi-lingual Knowledge Extraction, Clustering, Temporal Tracking and Hypothesis Generation System [PDF] [Project]
Manling Li, Ying Lin, Tuan Manh Lai, Xiaoman Pan, Haoyang Wen, Sha Li, etc %Zhenhailong Wang, Pengfei Yu, Lifu Huang, Di Lu, Qingyun Wang, Haoran Zhang, Qi Zeng, Chi Han, Zixuan Zhang, Yujia Qin, Xiaodan Hu, Nikolaus Parulian, Daniel Campos, Heng Ji, Brian Chen, Xudong Lin, Alireza Zareian, Amith Ananthram, Emily Allaway, Shih-Fu Chang, Kathleen McKeown, Yixiang Yao, Yifan Wang, Michael Spector, Mitchell DeHaven, Daniel Napierski, Marjorie Freedman, Pedro Szekely, Haidong Zhu, Ram Nevatia, Yang Bai, Yifan Wang, Ali Sadeghian, Haodi Ma, Daisy Zhe Wang
TAC-KBP: Text Analysis Conference Knowledge Base Population Workshop 2020 (Rank 1st in the leaderboard.)

Multimedia Knowledge ExtractionMultilingual Information ExtractionKnowledge Base Population

Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization
[PDF]
Manling Li, Lingyu Zhang, Heng Ji, Rich Radke
ACL'19: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp.2190–2196

Meeting SummarizationMultimodal SummarizationAbstractive Summarization

Multilingual Entity, Relation, Event and Human Value Extraction [PDF] [Code] [Video]
Manling Li, Ying Lin, Joe Hoover, Spencer Whitehead, Clare Voss, Morteza Dehghani, Heng Ji
NAACL'19: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp.110–115

Multilingual Information ExtractionEvent ExtractionHuman Values

GAIA at SM-KBP 2019 - A Multi-media Multi-lingual KnowledgeExtraction and Hypothesis Generation System [PDF] [Project]
Manling Li, Ying Lin, Ananya Subburathinam, Spencer Whitehead, Xiaoman Pan, Di Lu, Qingyun Wang, Tongtao Zhang, Lifu Huang, Heng Ji, Alireza Zareian, Hassan Akbari, Brian Chen, Bo Wu, Emily Allaway, Shih-Fu Chang, Kathleen McKeown, Yixiang Yao, Jennifer Chen, Eric Berquist, Kexuan Sun, Xujun Peng, Ryan Gabbard Marjorie Freedman, Pedro Szekely, T.K. Satish Kumar, Arka Sadhu, Ram Nevatia, Miguel Rodriguez, Yifan Wang, Yang Bai, Ali Sadeghian, Daisy Zhe Wang
TAC-KBP: Text Analysis Conference Knowledge Base Population Workshop 2019 (Rank 1st, with more than 10% higher than the second team.)

Multimedia Knowledge ExtractionMultilingual Information ExtractionKnowledge Base Population