Hyunwoo Kim, Kaist, Jinsung Yoon, Jeehye Na, Jongha Kim, Byungoh Ko
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Despite the remarkable capabilities of Large Vision Language Models (LVLMs), they still lack detailed knowledge about specific entities. Retrieval-augmented Generation (RAG) is a widely adopted solution that enhances LVLMs by providing additional contexts from an external Knowledge Base. However, we observe that previous decoding methods for RAG are sub-optimal as they fail to sufficiently leverage multiple relevant contexts and suppress the negative effects of irrelevant contexts. To this end, we propose Relevanceaware Multi-context Contrastive Decoding (RMCD), a novel decoding method for RAG. RMCD outputs a final prediction by combining outputs predicted with each context, where each output is weighted based on its relevance to the question. By doing so, RMCD effectively aggregates useful information from multiple relevant contexts while also counteracting the negative effects of irrelevant ones. Experiments show that RMCD consistently outperforms other decoding methods across multiple LVLMs, achieving the best performance on three knowledge-intensive visual questionanswering benchmarks. Also, RMCD can be simply applied by replacing the decoding method of LVLMs without additional training. Analyses also show that RMCD is robust to the retrieval results, consistently performing the best across the weakest to the strongest retrieval results. Code is available at https://github.com/mlvlab/RMCD.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.06050")
get_code_for_paper("2602.06050")
have("2602.06050")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.06050.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.06050)
Connect an agent — have() is free.