# shikiw/opera

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/shikiw-opera).**

411 stars · 33 forks · Python · MIT

## Links

- GitHub: https://github.com/shikiw/OPERA
- awesome-repositories: https://awesome-repositories.com/repository/shikiw-opera.md

## Topics

`chatbot` `chatgpt` `gpt-4` `large-multimodal-models` `llama` `multimodal` `vision-language-learning` `vision-language-model`

## Description

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

## Tags

### Part of an Awesome List

- [Hallucination Mitigation](https://awesome-repositories.com/f/awesome-lists/ai/hallucination-mitigation.md) — Over-trust penalty and retrospection-allocation to alleviate hallucinations.
- [Mitigation Methods](https://awesome-repositories.com/f/awesome-lists/ai/mitigation-methods.md) — Alleviates hallucination via over-trust penalty and retrospection.