A graph-based adapter that connects input, context, and knowledge tokens reduces hallucination in LLM question answering and improves RAG performance across several benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
A graph-based adapter that connects input, context, and knowledge tokens reduces hallucination in LLM question answering and improves RAG performance across several benchmarks.