# SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification

arXiv: https://arxiv.org/abs/2605.03701 · HTML: https://mlsanity.com/paper/2605.03701/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [In-Context Learning with Long-Context Models: An In-Depth Exploration](https://mlsanity.com/paper/2405.00200/) (2024)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Revisiting Demonstration Selection Strategies in In-Context Learning](https://mlsanity.com/paper/2401.12087/) (2024)
- [Reordering Examples Helps during Priming-based Few-Shot Learning](https://mlsanity.com/paper/2106.01751/) (2021)
- [When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks](https://mlsanity.com/paper/2311.08993/) (2023)
- [KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision](https://mlsanity.com/paper/2010.10833/) (2020)
- [Semantic Structure Enhanced Event Causality Identification](https://mlsanity.com/paper/2305.12792/) (2023)
- [Event Causality Identification with Synthetic Control](https://mlsanity.com/paper/2509.18156/) (2025)

## Built on by (most cited first, 1 of 1)

- [Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence](https://mlsanity.com/paper/2605.11348/) (2026)

## Abstract (arXiv)

Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination). To mitigate these issues and enhance LLM performance in ECI, we propose SERE, a structural example retrieval framework that leverages LLMs' few-shot learning capabilities. SERE introduces an innovative retrieval mechanism based on three structural concepts: (i) Conceptual Path Metric, which measures the conceptual relationship between events using edit distance in ConceptNet; (ii) Syntactic Metric, which quantifies structural similarity through tree edit distance on syntactic trees; and (iii) Causal Pattern Filtering, which filters examples based on predefined causal structures using LLMs. By integrating these structural retrieval strategies, SERE selects more relevant examples to guide LLMs in causal reasoning, mitigating bias and improving accuracy in ECI tasks. Extensive experiments on multiple ECI datasets validate the effectiveness of SERE. The source code is publicly available at https://github.com/DMIRLAB-Group/SERE.