Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/assertion>. }
Showing items 1 to 40 of
40
with 100 items per page.
- arXiv.2508.15790 type Entity assertion.
- ChatGPT4o type Workflow assertion.
- ChatGPT4oMini type Workflow assertion.
- DeepSeekR1 type Workflow assertion.
- GRPO type Workflow assertion.
- Gemini20FlashThinking type Workflow assertion.
- KGo1 type Workflow assertion.
- OpenO1 type Workflow assertion.
- O1Mini type Workflow assertion.
- QwQ32BPreview type Workflow assertion.
- ChatGPT4o label "ChatGPT-4o" assertion.
- ChatGPT4oMini label "ChatGPT4o-mini" assertion.
- DeepSeekR1 label "DeepSeek-R1" assertion.
- GRPO label "GRPO" assertion.
- Gemini20FlashThinking label "Gemini 2.0 Flash Thinking" assertion.
- KGo1 label "KG-o1" assertion.
- OpenO1 label "Open-o1" assertion.
- O1Mini label "o1-mini" assertion.
- QwQ32BPreview label "QwQ-32B-Preview" assertion.
- ChatGPT4o comment "ChatGPT-4o is an advanced general-purpose large language model (GPLLM) used in two contexts: first, as a tool to generate multi-hop questions for the KG-MHQA SFT dataset creation, and second, as a powerful baseline for performance comparison in the experiments." assertion.
- ChatGPT4oMini comment "ChatGPT4o-mini is an advanced general-purpose large language model (GPLLM) used as a baseline model for comparative evaluation against the proposed KG-o1 models on multi-hop reasoning tasks." assertion.
- DeepSeekR1 comment "DeepSeek-R1 is a specific large reasoning model (LRM) used as a strong baseline for evaluating the performance of KG-o1 models on multi-hop question answering datasets." assertion.
- GRPO comment "GRPO is a reinforcement learning method that serves as a comparative baseline in the ablation studies, where its performance in boosting LLMs' multi-hop reasoning is contrasted with other fine-tuning and optimization strategies, including the paper's Self-improved Adaptive DPO." assertion.
- Gemini20FlashThinking comment "Gemini 2.0 Flash Thinking is a specific large reasoning model (LRM) used as a strong baseline for evaluating the performance of KG-o1 models on multi-hop question answering tasks, highlighting its advanced reasoning capabilities." assertion.
- KGo1 comment "KG-o1 is a novel four-stage framework that integrates Knowledge Graphs (KGs) to enhance Large Language Models' (LLMs) multi-hop reasoning abilities. It involves constructing KG-derived datasets (KG-MHQA SFT and DPO) and using them to fine-tune LLMs (via Supervised Fine-Tuning and a "Self-improved Adaptive DPO" strategy), aiming to improve the LLM's intrinsic knowledge expression and reasoning capabilities during a training stage by internalizing logical paths." assertion.
- OpenO1 comment "Open-o1 is a specific influential large reasoning model (LRM) from the open-source community, used as a baseline for performance comparison in the experiments of the paper." assertion.
- O1Mini comment "o1-mini is a specific large reasoning model (LRM) mentioned as a prominent baseline for comparison against the proposed KG-o1 models in multi-hop question answering tasks." assertion.
- QwQ32BPreview comment "QwQ-32B-Preview is a specific large reasoning model (LRM) included as a prominent baseline for comparative experiments against the KG-o1 models on multi-hop reasoning tasks." assertion.
- KGo1 subject KGEnhancedLLMPretraining assertion.
- arXiv.2508.15790 title "KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration" assertion.
- arXiv.2508.15790 describes KGo1 assertion.
- arXiv.2508.15790 discusses ChatGPT4o assertion.
- arXiv.2508.15790 discusses ChatGPT4oMini assertion.
- arXiv.2508.15790 discusses DeepSeekR1 assertion.
- arXiv.2508.15790 discusses GRPO assertion.
- arXiv.2508.15790 discusses Gemini20FlashThinking assertion.
- arXiv.2508.15790 discusses OpenO1 assertion.
- arXiv.2508.15790 discusses O1Mini assertion.
- arXiv.2508.15790 discusses QwQ32BPreview assertion.
- KGo1 hasTopCategory KGEnhancedLLM assertion.