Research map / Large language models / Retrieval and knowledge
GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning
Jiale Fu, Yaqing Wang, Simeng Han, Jiaming Fan, Xu Yang
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 GraphIC retrieval instead of best baseline | GPT-4o-mini 8-shot · Average of 4 tasks | accuracy: 76.84/77.08 -> 78.26 | Improved |
| use GraphIC retrieval instead of best baseline | Llama-3.1-8B-Instruct 8-shot · Average of 4 tasks | accuracy: 68.33 -> 70.83 | Improved |
| GraphIC vs best baseline on MBPP | Llama-3.1-8B-Instruct · MBPP | accuracy: 62.4 -> 61.6 | Hurt |
| use FRR text embedding instead of raw question embedding (ablation) | Llama-3 retrieval · ProofWriter | accuracy: 73.75 -> 82.50 | Improved |
| use FRR text embedding instead of raw question embedding (ablation) | Llama-3 retrieval · GSM8K | accuracy: 74.15 -> 78.31 | Improved |
| convert FRR into thought graph embedding (ablation) | Llama-3 retrieval · AQUA | accuracy: 50.78 -> 54.72 | Improved |
| add reasoning-aware similarity metric with traceback (ablation) | Llama-3 graph retrieval · AQUA | accuracy: 54.72 -> 57.48 | Improved |
| add traceback mechanism (ablation) | Llama-3 graph similarity · AQUA | accuracy: 49.21 -> 57.48 | Improved |
| add proposed similarity (without traceback) (ablation) | Llama-3 graph retrieval · AQUA | accuracy: 54.72 -> 49.21 | Hurt |
| increase number of shots k from 1 to 8 | GraphIC vs baselines · GSM8K, AQUA, MBPP, ProofWriter | accuracy | Improved |
Closest papers by meaning
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.89)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.89)
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (ICLR 2024 · similarity 0.87)
- Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties (NeurIPS 2025 · similarity 0.87)
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models (ICML 2025 · similarity 0.87)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.87)
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.
