REVIEW 6 cited by
FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give the sequence-level reward for the whole response; and (3)Annotation cost is time-consuming and labor-intensive. To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward. Specifically, We first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm. Extensive experiments are conducted on hallucination and general benchmarks, demonstrating the superior performance of our proposed method. Notably, compared with previous models trained with the RL-based aligning method, our proposed method is effective even with fewer parameters.
Forward citations
Cited by 6 Pith papers
-
Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
RVCD uses YOLO detections and retrieved single-concept AI images to adjust LVLM logits at decode time, cutting CHAIR hallucination rates by roughly half versus prior contrastive decoding baselines.
-
AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs
A 600K-question audio-visual trustworthiness benchmark reveals that current AVLLMs are brittle under mismatches and missing modalities, and CAVPref, a calibrated preference-optimization method, improves their accuracy.
-
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
Nullu projects a vision-language model's weights into the null space of a subspace learned from truthful versus hallucinated captions, reducing object hallucinations without extra inference cost.
-
Wiener Representation Filtering for VLM Hallucination Suppression
A Wiener-style spectral filter, estimated from paired truthful and hallucinated hidden states and absorbed into feed-forward weights, suppresses object hallucination in VLMs without changing inference speed.
-
Empowering Multimodal LLMs with External Tools: A Comprehensive Survey
A survey paper maps how external tools are used to augment multimodal large language models across data, tasks, evaluation, and future directions.
-
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
A broad survey of LLM alignment that catalogs objectives, benchmarks, SFT/RLHF/DPO methods, and safety challenges, without contributing new experimental or theoretical results.
Discussion (0). Continue with ORCID to comment.