. . . . "KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration" . . . . . . . . . . . . . . . . "ChatGPT-4o" . . "ChatGPT4o-mini" . . "CoT (Chain-of-Thought)" . . "DPO (Direct Preference Optimization)" . . "DeepSeek-R1" . . "DeepSeek-R1-Distill-Qwen-14B" . . "GRPO" . . "Gemini 2.0 Flash Thinking" . . . "KG-o1 is a four-stage framework designed to enhance the intrinsic multi-hop reasoning abilities of LLMs. It leverages KGs to filter entities, generate logical paths, construct complex QA datasets for supervised fine-tuning (SFT) to simulate long-term thinking, and applies a Self-improved Adaptive DPO strategy to refine the LLMs' reasoning, ultimately improving LLM performance during inference for multi-hop question answering." . "KG-o1" . . . "Llama3.1-8B-Instruct" . . "Open-o1" . . "Qwen2.5-14B-Instruct" . . "Qwen2.5-7B-Instruct" . . . "2026-02-26T15:20:00.438Z"^^ . . . "LLM-KG assessment for paper 10.48550/arXiv.2508.15790" . "RSA" . "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB" . "lB2nfmt0OJSPkcOFwpwydOT9pxVhZUqrHYD/FPnULsl6T6+WjGndVvYofX5POflwoZ4/YCwcJI7XEpzFFAHBrzsRKTKGmXlgx/vjagtvGEgIE1PS6t3oLUJRJLVcv2vEFoXY1APT8knhPzaGWvhCVPiusD4IK1YsPvSU/8o91d8z61d8QG0WNxdno1T4qoHzkgxjsWGhb1b7Z4xLQWOol2cNs/GstQN2j/WZNUX5AXqQvdkp3O4FUBK84kyydLmf9+J95Pjf9/Z4RXsaNnNY31BrGKdF3ysmJpGErAzq9yalraRYYmE7u1bBEWLDD6hLLfI699T1OlTsSiL6PPLyNA==" . . .