Vincent Ng

AAAI Conference 2026 Conference Paper

CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking

• Zhiqiang Hao
• Chuanyi Li
• Ye Fan
• Jun Cai
• Xiao Fu
• Shangqi Wang
• Hao Shen
• Jiao Yin

We propose Contextual History for Adaptive and Simple Exploitation (CHASE), a novel multi-turn method for Large Language Model (LLM) jailbreaking. Rather than directly attack an LLM that may be difficult to jailbreak, CHASE first collects jailbroken histories from an easy-to-jailbreak LLM and then transfers them to the target LLM. Through this history transfer process, CHASE misleads the target LLM into thinking that it is responsible for producing the jailbroken histories and increases the chances of successful jailbreaking by prompting it to continue the conversation. Extensive evaluations on mainstream LLMs show that CHASE consistently achieves higher attack success rates and demands fewer computational resources compared to existing methods.

AAAI Conference 2026 Conference Paper

System L: Toward System 2-Style Legal Reasoning

• Chuanyi Li
• Yi Feng
• Vincent Ng

Dual-system theory distinguishes between fast, intuitive System 1 and slow, deliberative System 2. While this dichotomy describes many forms of reasoning, it oversimplifies the reality of expert legal reasoning. Legal reasoning is not merely a process of slow, logical deliberation. It is intrinsically normative, embedding precedent analysis, statutory interpretation, policy balancing, and social values. This paper envisions a reasoning architecture for legal reasoning, System L (Legal System 2), which extends traditional System 2 by integrating domain-specific normative frameworks in a structured manner. Using the IRAC (Issue–Rule–Application–Conclusion) structure as a backbone model, System L represents a blueprint for the next generation of cognitive and AI systems capable of human-like legal reasoning.

NeurIPS Conference 2025 Conference Paper

LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts

• Zhuo Han
• Yi Yang
• Yi Feng
• Wanhong Huang
• Ding Xuxing
• Chuanyi Li
• Jidong Ge
• Vincent Ng

Legal Judgment Prediction (LJP) seeks to predict case outcomes given available case information, offering practical value for both legal professionals and laypersons. However, a key limitation of existing LJP models is their limited adaptability to statutory revisions. Current SOTA models are neither designed nor evaluated for statutory revisions. To bridge this gap, we introduce LawShift, a benchmark dataset for evaluating LJP under statutory revisions. Covering 31 fine-grained change types, LawShift enables systematic assessment of SOTA models' ability to handle legal changes. We evaluate five representative SOTA models on LawShift, uncovering significant limitations in their response to legal updates. Our findings show that model architecture plays a critical role in adaptability, offering actionable insights and guiding future research on LJP in dynamic legal contexts.

AAAI Conference 2025 Conference Paper

Understanding Advertisements

• Yi Feng
• Chuanyi Li
• Vincent Ng

While AI systems are capable of reading texts and seeing images, they typically perceive surface information explicitly conveyed with limited abilities to comprehend hidden messages (e.g., a double-edged remark). We propose the novel task of advertisement understanding: given an advertisement, which can be a text, an image, or a video, the goal is to identify the persuasion strategies used and determine the (possibly hidden) messages conveyed. Efforts on this task could enhance machine comprehension capabilities, and provide users with increased situation awareness w.r.t. the advertised message and thus possibly enable mindful decision making. We believe that this task presents long-term challenges to AI researchers and that successful understanding of ads could bring machine understanding one important step closer to human understanding.

IJCAI Conference 2024 Conference Paper

Automated Essay Scoring: Recent Successes and Future Directions

• Shengjie Li
• Vincent Ng

Automated essay scoring (AES), the task of automatically assigning a score to an essay that summarizes its quality, is a challenging task that remains largely unsolved despite more than 50 years of research. This survey paper discusses the milestones in AES research and reflects on future directions.

AAAI Conference 2023 Conference Paper

Multimodal Propaganda Processing

• Vincent Ng
• Shengjie Li

Propaganda campaigns have long been used to influence public opinion via disseminating biased and/or misleading information. Despite the increasing prevalence of propaganda content on the Internet, few attempts have been made by AI researchers to analyze such content. We introduce the task of multimodal propaganda processing, where the goal is to automatically analyze propaganda content. We believe that this task presents a long-term challenge to AI researchers and that successful processing of propaganda could bring machine understanding one important step closer to human understanding. We discuss the technical challenges associated with this task and outline the steps that need to be taken to address it.

AAAI Conference 2022 Conference Paper

Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey

• Prajjwal Bhargava
• Vincent Ng

While commonsense knowledge acquisition and reasoning has traditionally been a core research topic in the knowledge representation and reasoning community, recent years have seen a surge of interest in the natural language processing community in developing pre-trained models and testing their ability to address a variety of newly designed commonsense knowledge reasoning and generation tasks. This paper presents a survey of these tasks, discusses the strengths and weaknesses of state-of-the-art pre-trained models for commonsense reasoning and generation as revealed by these tasks, and reflects on future research directions.

IJCAI Conference 2022 Conference Paper

Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code

• Changan Niu
• Chuanyi Li
• Bin Luo
• Vincent Ng

Recent years have seen the successful application of deep learning to software engineering (SE). In particular, the development and use of pre-trained models of source code has enabled state-of-the-art results to be achieved on a wide variety of SE tasks. This paper provides an overview of this rapidly advancing field of research and reflects on future research directions.

IJCAI Conference 2022 Conference Paper

Deexaggeration

• Li Kong
• Chuanyi Li
• Vincent Ng

We introduce a new task in hyperbole processing, deexaggeration, which concerns the recovery of the meaning of what is being exaggerated in a hyperbolic sentence in the form of a structured representation. In this paper, we lay the groundwork for the computational study of understanding hyperbole by (1) defining a structured representation to encode what is being exaggerated in a hyperbole in a non-hyperbolic manner, (2) annotating the hyperbolic sentences in two existing datasets, HYPO and HYPO-cn, using this structured representation, (3) conducting an empirical analysis of our annotated corpora, and (4) presenting preliminary results on the deexaggeration task.

IJCAI Conference 2022 Conference Paper

Legal Judgment Prediction: A Survey of the State of the Art

• Yi Feng
• Chuanyi Li
• Vincent Ng

Automatic legal judgment prediction (LJP) has recently received increasing attention in the natural language processing community in part because of its practical values as well as the associated research challenges. We present an overview of the major milestones made in LJP research covering multiple jurisdictions and multiple languages, and conclude with promising future research directions.

AAAI Conference 2021 Conference Paper

Span-Based Event Coreference Resolution

• Jing Lu
• Vincent Ng

Motivated by the recent successful application of span-based models to entity-based information extraction tasks, we investigate span-based models for event coreference resolution, focusing on determining (1) whether the successes of spanbased models of entity coreference can be extended to event coreference; (2) whether exploiting the dependency between event coreference and the related subtask of trigger detection; and (3) whether automatically computed entity coreference information can benefit span-based event coreference resolution. Empirical results on the standard evaluation dataset provide affirmative answers to all three questions.

AAAI Conference 2020 Conference Paper

Unveiling Hidden Intentions

• Gerardo Ocampo Diaz
• Vincent Ng

Recent years have seen significant advances in machine perception, which have enabled AI systems to become grounded in the world. While AI systems can now ”read” and ”see”, they still cannot read between the lines and see through the lens, unlike humans. We propose the novel task of hidden message and intention identification: given some perceptual input (i. e. , a text, an image), the goal is to produce a short description of the message the input transmits and the hidden intention of its author, if any. Not only will a solution to this task enable machine perception technologies to reach the next level of complexity, but it will be an important step towards addressing a task that has recently received a lot of public attention, political manipulation in social media.

AAAI Conference 2019 Conference Paper

Abstractive Summarization: A Survey of the State of the Art

• Hui Lin
• Vincent Ng

The focus of automatic text summarization research has exhibited a gradual shift from extractive methods to abstractive methods in recent years, owing in part to advances in neural methods. Originally developed for machine translation, neural methods provide a viable framework for obtaining an abstract representation of the meaning of an input text and generating informative, fluent, and human-like summaries. This paper surveys existing approaches to abstractive summarization, focusing on the recently developed neural approaches.

IJCAI Conference 2019 Conference Paper

Automated Essay Scoring: A Survey of the State of the Art

• Zixuan Ke
• Vincent Ng

Despite being investigated for over 50 years, the task of automated essay scoring is far from being solved. Nevertheless, it continues to draw a lot of attention in the natural language processing community in part because of its commercial and educational values as well as the associated research challenges. This paper presents an overview of the major milestones made in automated essay scoring research since its inception.

IJCAI Conference 2018 Conference Paper

Event Coreference Resolution: A Survey of Two Decades of Research

• Jing Lu
• Vincent Ng

Recent years have seen a gradual shift of focus from entity-based tasks to event-based tasks in information extraction research. Being a core event-based task, event coreference resolution is less studied but arguably more challenging than entity coreference resolution. This paper provides an overview of the major milestones made in event coreference research since its inception two decades ago.

IJCAI Conference 2018 Conference Paper

Learning to Give Feedback: Modeling Attributes Affecting Argument Persuasiveness in Student Essays

• Zixuan Ke
• Winston Carlile
• Nishant Gurrapadi
• Vincent Ng

Argument persuasiveness is one of the most important dimensions of argumentative essay quality, yet it is little studied in automated essay scoring research. Using a recently released corpus of essays that are simultaneously annotated with argument components, argument persuasiveness scores, and attributes of argument components that impact an argument’s persuasiveness, we design and train the first set of neural models that predict the persuasiveness of an argument and its attributes in a student essay, enabling useful feedback to be provided to students on why their arguments are (un)persuasive in addition to how persuasive they are.

AAAI Conference 2017 Conference Paper

Machine Learning for Entity Coreference Resolution: A Retrospective Look at Two Decades of Research

• Vincent Ng

Though extensively investigated since the 1960s, entity coreference resolution, a core task in natural language understanding, is far from being solved. Nevertheless, significant progress has been made on learning-based coreference research since its inception two decades ago. This paper provides an overview of the major milestones made in learningbased coreference research and discusses a hard entity coreference task, the Winograd Schema Challenge, which has recently received a lot of attention in the AI community.

IJCAI Conference 2017 Conference Paper

Why Can't You Convince Me? Modeling Weaknesses in Unpersuasive Arguments

• Isaac Persing
• Vincent Ng

Recent work on argument persuasiveness has focused on determining how persuasive an argument is. Oftentimes, however, it is equally important to understand why an argument is unpersuasive, as it is difficult for an author to make her argument more persuasive unless she first knows what errors made it unpersuasive. Motivated by this practical concern, we (1) annotate a corpus of debate comments with not only their persuasiveness scores but also the errors they contain, (2) propose an approach to persuasiveness scoring and error identification that outperforms competing baselines, and (3) show that the persuasiveness scores computed by our approach can indeed be explained by the errors it identifies.

AAAI Conference 2016 Conference Paper

Joint Inference over a Lightly Supervised Information Extraction Pipeline: Towards Event Coreference Resolution for Resource-Scarce Languages

• Chen Chen
• Vincent Ng

We address two key challenges in end-to-end event coreference resolution research: (1) the error propagation problem, where an event coreference resolver has to assume as input the noisy outputs produced by its upstream components in the standard information extraction (IE) pipeline; and (2) the data annotation bottleneck, where manually annotating data for all the components in the IE pipeline is prohibitively expensive. This is the case in the vast majority of the world’s natural languages, where such annotated resources are not readily available. To address these problems, we propose to perform joint inference over a lightly supervised IE pipeline, where all the models are trained using either active learning or unsupervised learning. Using our approach, only 25% of the training sentences in the Chinese portion of the ACE 2005 corpus need to be annotated with entity and event mentions in order for our event coreference resolver to surpass its fully supervised counterpart in performance.

AAAI Conference 2015 Conference Paper

Chinese Common Noun Phrase Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

• Chen Chen
• Vincent Ng

AAAI Conference 2014 Conference Paper

Chinese Overt Pronoun Resolution: A Bilingual Approach

• Chen Chen
• Vincent Ng

AAAI Conference 2014 Conference Paper

Chinese Zero Pronoun Resolution: An Unsupervised Approach Combining Ranking and Integer Linear Programming

• Chen Chen
• Vincent Ng

AAAI Conference 2012 Conference Paper

Clustering Documents Along Multiple Dimensions

• Sajib Dasgupta
• Richard Golden
• Vincent Ng

Traditional clustering algorithms are designed to search for a single clustering solution despite the fact that multiple alternative clustering solutions might exist for a particular dataset. For example, a set of news articles might be clustered by topic or by the author’s gender or age. Similarly, book reviews might be clustered by sentiment or comprehensiveness. In this paper, we address the problem of identifying alternative clustering solutions by developing a Probabilistic Multi-Clustering (PMC) model that discovers multiple, maximally different clusterings of a data sample. Empirical results on six datasets representative of real-world applications show that our PMC model exhibits superior performance to comparable multi-clustering algorithms.

IJCAI Conference 2011 Conference Paper

Ensemble-Based Coreference Resolution

• Altaf Rahman
• Vincent Ng

We investigate new methods for creating and applying ensembles for coreference resolution. While existing ensembles for coreference resolution are typically created using different learning algorithms, clustering algorithms or training sets, we harness recent advances in coreference modeling and propose to create our ensemble from a variety of supervised coreference models. However, the presence of pairwise and non-pairwise coreference models in our ensemble presents a challenge to its application: it is not immediately clear how to combine the coreference decisions made by these models. We investigate different methods for applying a model-heterogeneous ensemble for coreference resolution. Empirical results on the ACE data sets demonstrate the promise of ensemble approaches: all ensemble-based systems significantly outperform the best member of the ensemble.

IJCAI Conference 2011 Conference Paper

Learning Cause Identifiers from Annotator Rationales

• Muhammad Arshad Ul Abedin
• Vincent Ng
• Latifur Rahman Khan

In the aviation safety research domain, cause identification refers to the task of identifying the possible causes responsible for the incident describedin an aviation safety incident report. This task presents a number of challenges, including the scarcity of labeled data and the difficulties in finding the relevant portions of the text. We investigate the use of annotator rationales to overcome these challenges, proposing several new ways of utilizing rationales and showing that through judicious use of the rationales, it is possible to achieve significant improvement over a unigram SVM baseline.

IJCAI Conference 2011 Conference Paper

Simple and Fast Strong Cyclic Planning for Fully-Observable Nondeterministic Planning Problems

• Jicheng Fu
• Vincent Ng
• Farokh B. Bastani
• I-Ling Yen

We address a difficult, yet under-investigated class of planning problems: fully-observable nondeterministic (FOND) planning problems with strong cyclic solutions. The difficulty of these strong cyclic FOND planning problems stems from the large size of the state space. Hence, to achieve efficient planning, a planner has to cope with the explosion in the size of the state space by planning along the directions that allow the goal to be reached quickly. A major challenge is: how would one know which states and search directions are relevant before the search for a solution has even begun? We first describe an NDP-motivated strong cyclic algorithm that, without addressing the above challenge, can already outperform state-of-the-art FOND planners, and then extend this NDP-motivated planner with a novel heuristic that addresses the challenge.

IJCAI Conference 2007 Conference Paper

• Vincent Ng

This paper focuses on the linguistic aspect of noun phrase coreference, investigating the knowledge sources that can potentially improve a learning-based coreference resolution system. Unlike traditional, knowledge-lean coreference resolvers, which rely almost exclusively on morpho-syntactic cues, we show how to induce features that encode semantic knowledge from labeled and unlabeled corpora. Experiments on the ACE data sets indicate that the addition of these new semantic features to a coreference system employing a fairly standard feature set significantly improves its performance.

AAAI Conference 2005 Conference Paper

Supervised Ranking for Pronoun Resolution: Some Recent Improvements

• Vincent Ng

A recently-proposed machine learning approach to reference resolution — the twin-candidate approach — has been shown to be more promising than the traditional single-candidate approach. This paper presents a pronoun interpretation system that extends the twin-candidate framework by (1) equipping it with the ability to identify non-referential pronouns, (2) training different models for handling different types of pronouns, and (3) incorporating linguistic knowledge sources that are generally not employed in traditional pronoun resolvers. The resulting system, when evaluated on a standard coreference corpus, outperforms not only the original twin-candidate approach but also a state-of-the-art pronoun resolver.