Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation

2025-04-13

AI Summary

This work addresses key challenges in end-to-end fine-grained sentiment–cause–category triplet extraction: difficulty modeling implicit/ambiguous sentiments, strong interference from redundant information, and severe scarcity of annotated data. We propose an instruction-tuning framework that integrates LoRA-based low-rank adaptation, task-oriented prompt engineering, and LLM-driven controllable synthetic data augmentation—eliminating the need for complex custom architectures while enabling unified span-level triplet modeling. Our core innovation lies in synergistically coupling instruction tuning with prompt-guided data expansion to enhance structured triplet generation, particularly improving implicit sentiment recognition. On standard benchmarks, our approach achieves an absolute F1-score gain of ≥12.8% over state-of-the-art methods, effectively mitigating data sparsity and noise interference.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis. This task involves identifying emotion spans, cause spans, and their associated emotion categories within the text to form structured triplets. While prior research has predominantly concentrated on clause-level emotion-cause pair extraction and span-level emotion-cause detection, these methods often confront challenges originating from redundant information retrieval and difficulty in accurately determining emotion categories, particularly when emotions are expressed implicitly or ambiguously. To overcome these challenges, this study explores a fine-grained approach to span-level emotion-cause-category triplet extraction and introduces an innovative framework that leverages instruction tuning and data augmentation techniques based on large language models. The proposed method employs task-specific triplet extraction instructions and utilizes low-rank adaptation to fine-tune large language models, eliminating the necessity for intricate task-specific architectures. Furthermore, a prompt-based data augmentation strategy is developed to address data scarcity by guiding large language models in generating high-quality synthetic training data. Extensive experimental evaluations demonstrate that the proposed approach significantly outperforms existing baseline methods, achieving at least a 12.8% improvement in span-level emotion-cause-category triplet extraction metrics. The results demonstrate the method's effectiveness and robustness, offering a promising avenue for advancing research in emotion cause analysis. The source code is available at https://github.com/zxgnlp/InstruDa-LLM.

Problem

• Extracting emotion-cause-category triplets at span level
• Overcoming redundant information retrieval challenges
• Addressing data scarcity with synthetic training data

Innovation

• Instruction tuning LLMs for triplet extraction
• Low-rank adaptation fine-tunes large models
• Prompt-based data augmentation generates synthetic data