TRIZ-RAGNER: A Retrieval-Augmented Large Language Model for TRIZ-Aware Named Entity Recognition in Patent-Based Contradiction Mining

TL;DR

TRIZ-RAGNER is a novel retrieval-augmented large language model framework that improves TRIZ-aware named entity recognition in patent contradiction mining by integrating domain knowledge and advanced retrieval techniques.

Contribution

It introduces a retrieval-augmented LLM approach that reformulates contradiction mining as a semantic NER task, enhancing accuracy and consistency over traditional methods.

Findings

Achieves 84.2% F1-score in TRIZ contradiction pair identification.

Outperforms baseline models with a 7.3 percentage point F1-score improvement.

Demonstrates effective knowledge grounding reduces semantic noise.

Abstract

TRIZ-based contradiction mining is a fundamental task in patent analysis and systematic innovation, as it enables the identification of improving and worsening technical parameters that drive inventive problem solving. However, existing approaches largely rely on rule-based systems or traditional machine learning models, which struggle with semantic ambiguity, domain dependency, and limited generalization when processing complex patent language. Recently, large language models (LLMs) have shown strong semantic understanding capabilities, yet their direct application to TRIZ parameter extraction remains challenging due to hallucination and insufficient grounding in structured TRIZ knowledge. To address these limitations, this paper proposes TRIZ-RAGNER, a retrieval-augmented large language model framework for TRIZ-aware named entity recognition in patent-based contradiction mining. TRIZ-RAGNER reformulates contradiction mining as a semantic-level NER task and integrates dense retrieval over a TRIZ knowledge base, cross-encoder reranking for context refinement, and structured LLM prompting to extract improving and worsening parameters from patent sentences. By injecting domain-specific TRIZ knowledge into the LLM reasoning process, the proposed framework effectively reduces semantic noise and improves extraction consistency. Experiments on the PaTRIZ dataset demonstrate that TRIZ-RAGNER consistently outperforms traditional sequence labeling models and LLM-based baselines. The proposed framework achieves a precision of 85.6%, a recall of 82.9%, and an F1-score of 84.2% in TRIZ contradiction pair identification. Compared with the strongest baseline using prompt-enhanced GPT, TRIZ-RAGNER yields an absolute F1-score improvement of 7.3 percentage points, confirming the effectiveness of retrieval-augmented TRIZ knowledge grounding for robust and accurate patent-based contradiction mining.