Research map / Large language models / Retrieval and knowledge

GEAR-Up: Generative AI and External Knowledge-Based Retrieval: Upgrading Scholarly Article Searches for Systematic Reviews

AAAI 2024 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Demonstrates GEAR-Up, a modular system that expands user queries with knowledge graph and masked language model context, generates related queries with ChatGPT, and retrieves scholarly articles via PubMed and a FAISS retriever to assist systematic reviews, qualitatively checked by a librarian.

Problem

Systematic reviews are time-intensive and require significant librarian effort to formulate queries and search scholarly databases.

Approach

Combine LLM-based query reformulation (ChatGPT) with knowledge graph and masked language model query expansion, then retrieve PubMed articles and rank them with a FAISS retriever, so that the first steps of systematic review (question formulation and protocol-based query building) are automated with librarian feedback.

Key results

• The system retrieves articles for user queries and was qualitatively compared against sentinel ground-truth articles from an in-house librarian; no quantitative metrics are reported in the text.
• Librarian review reportedly shows favorable results in reducing librarian burden by providing high-quality articles similar to a human librarian.

Limitations

• Evaluation is qualitative and relies on a single in-house librarian and sentinel articles.
• ChatGPT may generate irrelevant or incoherent queries without librarian refinement.
• Safety controls for sensitive content (e.g., drug misuse) are proposed but not implemented or evaluated.

Experimental setup

Datasets: PubMed knowledge graphs

Metrics: qualitative librarian review

Builds on: Retrieval-Augmented Generation ChatGPT

Closest papers by meaning

• Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs (AAAI 2025 · similarity 0.85)
• DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation (NeurIPS 2025 · similarity 0.84)
• Learning to Rank in Generative Retrieval (AAAI 2024 · similarity 0.84)
• OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework (NeurIPS 2026 · similarity 0.84)
• Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting (ICLR 2025 · similarity 0.84)
• KnowPO: Knowledge-Aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models (AAAI 2025 · similarity 0.84)