Research map / Large language models / Agents, code and math
GSAP-ERE: Fine-Grained Scholarly Entity and Relation Extraction Focused on Machine Learning
Wolfgang Otto, Lu Gan, Sharmila Upadhyaya, Saurav Karmakar, Stefan Dietze
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use joint extraction (HGERE) instead of pipeline (PL-Marker) | fine-tuned SciBERT ERE models · GSAP-ERE test | RE F1: 41.4 -> 54.0 | Improved |
| fine-tune on GSAP-ERE instead of prompting an LLM | entity and relation extraction · GSAP-ERE test | NER F1: 44.4 -> 80.6 | Improved |
| fine-tune on GSAP-ERE instead of prompting an LLM | entity and relation extraction · GSAP-ERE test | RE F1: 10.1 -> 54.0 | Improved |
| use similar+diverse example selection instead of random (ablation) | Qwen2.5-32B few-shot NER · GSAP-ERE validation | NER≈ F1 (10-shot): 53.3 -> 58.4 | Improved |
| increase few-shot examples from 10 to 20 with similar+diverse selection (ablation) | Qwen2.5-32B few-shot NER · GSAP-ERE validation | NER≈ F1: 58.4 -> 39.4 | Hurt |
| add few-shot examples to the RE prompt (0 -> 1 shot) (ablation) | Qwen2.5-32B few-shot RE · GSAP-ERE validation | RE≈ F1: 16.8 -> 20.4 | Improved |
| increase RE shots from 2 to 5 (ablation) | Qwen2.5-32B few-shot RE · GSAP-ERE validation | RE≈ F1: 20.5 -> 19.9 | No clear effect |
| use larger LLM (Qwen 72b instead of 32b) | LLM prompting pipeline · GSAP-ERE test | RE F1: 7.2 -> 10.1 | Improved |
Closest papers by meaning
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.85)
- STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models (AAAI 2024 · similarity 0.84)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.84)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.84)
- Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI 2024 · similarity 0.84)
- Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
