REVIEW 6 cited by
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment
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
Signed reviews
read the original abstract
As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and time-intensive. In this paper, we investigate the efficacy of AI feedback to scale supervision for aligning LVLMs. We introduce VLFeedback, the first large-scale vision-language feedback dataset, comprising over 82K multi-modal instructions and comprehensive rationales generated by off-the-shelf models without human annotations. To evaluate the effectiveness of AI feedback for vision-language alignment, we train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback. Silkie showcases exceptional performance regarding helpfulness, visual faithfulness, and safety metrics. It outperforms its base model by 6.9\% and 9.5\% in perception and cognition tasks, reduces hallucination issues on MMHal-Bench, and exhibits enhanced resilience against red-teaming attacks. Furthermore, our analysis underscores the advantage of AI feedback, particularly in fostering preference diversity to deliver more comprehensive improvements. Our dataset, training code and models are available at https://vlf-silkie.github.io.
Forward citations
Cited by 6 Pith papers
-
Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
Modality bias, an imbalanced attention to text or image during hallucinated outputs, is shown to be mitigated by a training-free attention intervention plus contrastive decoding.
-
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
SynthRL synthesizes harder, answer-preserving visual math questions from easy seed questions and reports small but mixed out-of-domain RLVR gains for Qwen2.5-VL-7B.
-
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
IXC-2.5-Reward is an open-source multimodal reward model that achieves 70.0% macro accuracy on VL-RewardBench and improves LVLM chat via PPO.
-
Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput
Flash-VL 2B is a 2-billion-parameter vision-language model with higher measured throughput than similar 2B models and slightly better average benchmark scores, thanks to a new image-tiling method.
-
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
DAMA scales the DPO penalty per example using CLIP-derived data hardness and current model reward gaps, and is reported to improve hallucination and general benchmarks for LLaVA-1.5 7B and 13B.
-
A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
A position paper arguing that LLM-based human-agent systems, not fully autonomous agents, should be the immediate goal for AI development.
Discussion (0). Continue with ORCID to comment.