Lune

ACL Findings2026

EPIR: Capturing Promoting and Inhibiting Relationships between Events

Bowen Dong, Wenjun Wang, Xueli Liu, Quanlin Qiu

Abstract

Understanding whether one event increases or decreases the likelihood of another is critical for real-life applications. Unlike other relationships, promoting and inhibiting relationships capture directional, probabilistic, and contextdependent shifts in event likelihood. A central challenge is to estimate this relative influence from observational data: naive conditional probabilities conflate influence with correlation and are easily distorted by shared contextual confounders. We propose EPIR, a unified framework for estimating promoting and inhibiting relationships from observed event data. EPIR formulates influence as a relative directional effect under comparable contextual conditions, and models event context using : (i) observable history captured and (ii) latent multi-hop propagation mechanisms. EPIR combines context-conditioned predictive evidence with schema-based structural evidence to produce a single signed influence score, where the sign determines promotion versus inhibition. Experiments on realworld datasets show that EPIR outperforms other baselines in accuracy. EPIR is available at https://github.com/EveLappland/EPIR.git.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. RNNLogic: Learning Logic Rules for Reasoning on Knowledge GraphsMeng Qu, Jun-Kun Chen, Louis-Pascal A. C. Xhonneux, Yoshua Bengio et al.ICLR 2021 · 230 citations
  2. SDGNN: Learning Node Representation for Signed Directed NetworksJunjie Huang, Huawei Shen, Liang Hou, Xueqi ChengAAAI 2021 · 128 citations
  3. Joint Constrained Learning for Event-Event Relation ExtractionHaoyu Wang, Muhao Chen, Hongming Zhang, Dan RothEMNLP 2020 · 105 citations
  4. Event-Driven Continuous Time Bayesian NetworksDebarun Bhattacharjya, Karthikeyan Shanmugam, Tian Gao, Nicholas Mattei et al.AAAI 2020 · 21 citations
  5. Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge GraphZhiyu Fang, Shuai-Long Lei, Xiaobin Zhu, Chun Yang et al.SIGIR 2024 · 17 citations

Related papers

  1. Probabilistic Attention-to-Influence Neural Models for Event SequencesXiao Shou, Debarun Bhattacharjya, Tian Gao, Dharmashankar Subramanian et al.ICML 2023 · 4 citations
  2. On Measuring Influence in Avoiding Undesired FutureLue Tao, Tian-Zuo Wang, Yuan Jiang, Zhi-Hua ZhouICLR 2026
  3. Pairwise Causality Guided Transformers for Event SequencesXiao Shou, Debarun Bhattacharjya, Tian Gao, Dharmashankar Subramanian et al.NeurIPS 2023 · 6 citations
  4. Bayesian Active Learning for Bivariate Causal DiscoveryYuxuan Wang, Mingzhou Liu, Xinwei Sun, Wei Wang et al.ICML 2025
  5. PRESCRIBE: Predicting Single-Cell Responses with Bayesian EstimationJiabei Cheng, Changxi Chi, Jingbo Zhou, Hongyi Xin et al.NeurIPS 2025 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines