SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.09729 · 2023

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
wyl-willing/MindMap canonical 6 of 8
FunctionStatusWhere it lives
chat Ran wyl-willing/MindMap/pre-training/explainpe/keyword.py
pointer only (licence: NONE) · get_code("b759881245a90f3e")
chat_35 Ran wyl-willing/MindMap/MindMap.py
pointer only (licence: NONE) · get_code("5e07cc24a99e649e")
chat_4 Ran wyl-willing/MindMap/MindMap.py
pointer only (licence: NONE) · get_code("c6c612f4e7f41ed4")
prompt_comparation Ran wyl-willing/MindMap/evaluation/gpt4_preference_drug.py
pointer only (licence: NONE) · get_code("7be86cacefea6f89")
prompt_comparation Ran wyl-willing/MindMap/evaluation/gpt4_preference_total.py
pointer only (licence: NONE) · get_code("f826b5a33b16da28")
row_to_string Ran wyl-willing/MindMap/pre-training/chatdoctor5k/csvTodocument.py
pointer only (licence: NONE) · get_code("0276dad790bbbcfc")
is_unable_to_answer Not yet run wyl-willing/MindMap/pre-training/chatdoctor5k/csvTodocument.py
pointer only (licence: NONE) · get_code("ba946e72117a1df4")
prompt_comparation Not yet run wyl-willing/MindMap/evaluation/gpt4_preference_disease.py
pointer only (licence: NONE) · get_code("eb72fd9471b417f2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks. However, they often suffer from limitations such as difficulty in incorporating new knowledge, generating hallucinations, and explaining their reasoning process. To address these challenges, we propose a novel prompting pipeline, named \method, that leverages knowledge graphs (KGs) to enhance LLMs' inference and transparency. Our method enables LLMs to comprehend KG inputs and infer with a combination of implicit and external knowledge. Moreover, our method elicits the mind map of LLMs, which reveals their reasoning pathways based on the ontology of knowledge. We evaluate our method on diverse question \& answering tasks, especially in medical domains, and show significant improvements over baselines. We also introduce a new hallucination evaluation benchmark and analyze the effects of different components of our method. Our results demonstrate the effectiveness and robustness of our method in merging knowledge from LLMs and KGs for combined inference. To reproduce our results and extend the framework further, we make our codebase available at https://github.com/wyl-willing/MindMap.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.09729")
get_code_for_paper("2308.09729")
have("2308.09729")

Connect an agent — have() is free.