Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge g
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Northwind AI →
- PossiblePossibly related (embedding) · 48%EY re-envisions RAG around multimodal knowledge graphs to improve accuracy - SiliconANGLE →
- PossiblePossibly related (embedding) · 47%Knowledge Distillation of Black-Box Large Language Models →
- LinkedLinked via arxiv author · 85%Peiji Yu →
“Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph”
- LinkedLinked via arxiv author · 85%Xin Cheng →
“Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph”
- LinkedLinked via arxiv author · 85%Tianxing Wu →
“Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph”
- FuzzyOverlapping authors or contributors · 62%DietrichGebert/ponytail →
“Shared author/contributor keys: cheng”
- FuzzySimilar title/name (fuzzy) · 59%tirth8205/code-review-graph →
“Fuzzy title match (0.73): “Debate-on-Graph: Reliable and Adaptive Reasoning of Large La” ≈ “tirth8205/code-review-graph””