이진욱님의 블로그

https://arxiv.org/abs/2402.03746

https://arxiv.org/pdf/2309.14525 Large Multimodal Models (LMM) are built across modalities and the misalign-ment between two modalities can result in “hallucination”, generating textual out-puts that are not grounded by the multimodal information in context. To address the multimodal misalignment issue, we adapt the Reinforcement Learning from Human Feedback (RLHF) from the text domain to the ta..

https://arxiv.org/pdf/2406.07476

https://arxiv.org/pdf/2403.15377

https://arxiv.org/pdf/2402.13217

https://arxiv.org/pdf/2407.00369 Large language or multimodal model based verification has been proposed to scale up online policing mechanisms for mitigating spread of false and harmful content.

unit tests, proof checkers, majority voting를 verifier로 써서 inference scaling law를 연구

https://arxiv.org/pdf/2405.07863

https://arxiv.org/pdf/2406.01297Self-correction is an approach to improving responses from large language models (LLMs) by refining the responses using LLMs during inference. Prior work has proposed various self-correction frameworks using different sources of feedback, including self-evaluation and external feedback. However, there is still no consensus on the question of when LLMs can correct ..