Xiaogang Xu, Piji Li, Fan Yuan, Chi Qin
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.
Large Vision-Language Models (LVLMs) have shown remarkable performance on many visuallanguage tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the images. Many existing work detects hallucination by directly judging whether an object exists in an image, overlooking the association between the object and semantics. To address this issue, we propose Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding (HELPD). This framework incorporates hallucination feedback at both object and sentence semantic levels. Remarkably, even with a marginal degree of training, this approach can alleviate over 15% of hallucination. Simultaneously, HELPD penalizes the output logits according to the image attention window to avoid being overly affected by generated text. HELPD can be seamlessly integrated with any LVLMs. Our experiments demonstrate that the proposed framework yields favorable results across multiple hallucination benchmarks. It effectively mitigates hallucination for different LVLMs and concurrently improves their text generation quality. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.20429")
get_code_for_paper("2409.20429")
have("2409.20429")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.20429.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.20429)
Connect an agent — have() is free.