Papers by Guangjun Zhang

4 papers
Dynamic Energy-Based Contrastive Learning with Multi-Stage Knowledge Verification for Event Causality Identification (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for event causal identification rely on rule-based or random sampling strategies, which introduce spurious causal positives.
Approach: They propose an ECI method enhanced by Dynamic Energy-based Contrastive Learning with multi-stage knowledge verification which generates high-quality contrastive samples and effectively suppresses spurious causal disturbances.
Outcome: The proposed method outperforms state-of-the-art methods on two benchmarks.
Hyperspherical Multi-Prototype with Optimal Transport for Event Argument Extraction (2024.acl-long)

Copied to clipboard

Challenge: Event Argument Extraction (EAE) aims to extract arguments for specified events from a text . previous work focused on long-distance dependencies of arguments, modeling co-occurrence relationships .
Approach: They propose a model that takes inductive biases as targets to locate prototypes . they set multiple prototypes to represent each role to capture intra-class differences .
Outcome: The proposed model achieves state-of-the-art on the RAMS and WikiEvents datasets.
Enhancing Event Causality Identification with LLM Knowledge and Concept-Level Event Relations (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to identify causal relationships between events often overlook the dependencies between similar events.
Approach: They propose an ECI method enhanced by LLM Knowledge and Concept-Level Event Relations (LKCER) the method constructs a conceptual-level heterogeneous event graph by leveraging local contextual information of related event mentions.
Outcome: The proposed method outperforms previous state-of-the-art methods on both benchmarks, EventStoryLine and Causal-TimeBank.
Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for logical reasoning with large language models suffer from insufficient rule semantic grounding and weak rule application mechanisms.
Approach: They propose a theory-of-mind driven neuro-symbolic reasoning framework that integrates natural language and symbolic representations throughout the reasoning process.
Outcome: The proposed model surpasses state-of-the-art models in reasoning accuracy and flexibility.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations