Ximing Wen

AAAI Conference 2025 Short Paper

Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks

• Ximing Wen

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My dissertation focuses on developing intrinsically interpretable models when using LMs as encoders while maintaining their superior performance via prototypical networks. I initiated my research by investigating enhancements in performance for interpretable models of sarcasm detection. My proposed approach focuses on capturing sentiment incongruity to enhance accuracy while offering instance-based explanations for the classification decisions. Later, we develop a novel white-box multi-head graph attention-based prototypical framework designed to explain the decisions of text classification models without sacrificing the accuracy of the original black-box LMs. In addition, I am working on extending the attention-based prototypical framework with contrastive learning to redesign an interpretable graph neural network for document classification, aiming to enhance both the interpretability and performance of the model in document classification.

AAAI Conference 2019 Conference Paper

Disjunctive Normal Form for Multi-Agent Modal Logics Based on Logical Separability

• Liangda Fang
• Kewen Wang
• Zhe Wang
• Ximing Wen

Modal logics are primary formalisms for multi-agent systems but major reasoning tasks in such logics are intractable, which impedes applications of multi-agent modal logics such as automatic planning. One technique of tackling the intractability is to identify a fragment called a normal form of multiagent logics such that it is expressive but tractable for reasoning tasks such as entailment checking, bounded conjunction transformation and forgetting. For instance, DNF of propositional logic is tractable for these reasoning tasks. In this paper, we first introduce a notion of logical separability and then define a novel disjunctive normal form SDNF for the multiagent logic Kn, which overcomes some shortcomings of existing approaches. In particular, we show that every modal formula in Kn can be equivalently casted as a formula in SDNF, major reasoning tasks tractable in propositional DNF are also tractable in SDNF, and moreover, formulas in SDNF enjoy the property of logical separability. To demonstrate the usefulness of our approach, we apply SDNF in multi-agent epistemic planning. Finally, we extend these results to three more complex multi-agent logics Dn, K45n and KD45n.

KR Conference 2018 Short Paper

Knowledge Compilation in Multi-Agent Epistemic Logics

• Liangda Fang
• Kewen Wang
• Zhe Wang
• Ximing Wen

IJCAI Conference 2015 Conference Paper

On the Progression of Knowledge and Belief for Nondeterministic Actions in the Situation Calculus

• Liangda Fang
• Yongmei Liu
• Ximing Wen

In a seminal paper, Lin and Reiter introduced the notion of progression for basic action theories in the situation calculus. Recently, Fang and Liu extended the situation calculus to account for multi-agent knowledge and belief change. In this paper, based on their framework, we investigate progression of both belief and knowledge in the single-agent propositional case. We first present a model-theoretic definition of progression of knowledge and belief. We show that for propositional actions, i. e. , actions whose precondition axioms and successor state axioms are propositional formulas, progression of knowledge and belief reduces to forgetting in the logic of knowledge and belief, which we show is closed under forgetting. Consequently, we are able to show that for propositional actions, progression of knowledge and belief is always definable in the logic of knowledge and belief.

IJCAI Conference 2013 Conference Paper

Multi-Agent Epistemic Explanatory Diagnosis via Reasoning about Actions

• Quan Yu
• Ximing Wen
• Yongmei Liu

The task of explanatory diagnosis conjectures actions to explain observations. This is a common task in real life and an essential ability of intelligent agents. It becomes more complicated in multi-agent scenarios, since agents’ actions may be partially observable to other agents, and observations might involve agents’ knowledge about the world or other agents’ knowledge or even common knowledge of a group of agents. For example, we might want to explain the observation that p does not hold, but Ann believes p, or the observation that Ann, Bob, and Carl commonly believe p. In this paper, we formalize the multi-agent explanatory diagnosis task in the framework of dynamic epistemic logic, where Kripke models of actions are used to represent agents’ partial observability of actions. Since this task is undecidable in general, we identify important decidable fragments via techniques of reducing the potentially infinite search spaces to finite ones of epistemic states or action sequences.

IJCAI Conference 2011 Conference Paper

On the Progression of Knowledge in the Situation Calculus

• Yongmei Liu
• Ximing Wen

In a seminal paper, Lin and Reiter introduced the notion of progression for basic action theories in the situation calculus. Earlier works by Moore, Scherl and Levesque extended the situation calculus to account for knowledge. In this paper, we study progression of knowledge in the situation calculus. We first adapt the concept of bisimulation from modal logic and extend Lin and Reiter's notion of progression to accommodate knowledge. We show that for physical actions, progression of knowledge reduces to forgetting predicates in first-order modal logic. We identify a class of first-order modal formulas for which forgetting an atom is definable in first-order modal logic. This class of formulas goes beyond formulas without quantifying-in. We also identify a simple case where forgetting a predicate reduces to forgetting a finite number of atoms. Thus we are able to show that for local-effect physical actions, when the initial KB is a formula in this class, progression of knowledge is definable in first-order modal logic. Finally, we extend our results to the multi-agent case.