REVIEW 13 cited by
Calibrated Self-Rewarding Vision Language Models
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 made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image, indicating a misalignment between image and text pairs. This misalignment arises because the model tends to prioritize textual information over visual input, even when both the language model and visual representations are of high quality. Existing methods leverage additional models or human annotations to curate preference data and enhance modality alignment through preference optimization. These approaches may not effectively reflect the target LVLM's preferences, making the curated preferences easily distinguishable. Our work addresses these challenges by proposing the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning. In the reward modeling, we employ a step-wise strategy and incorporate visual constraints into the self-rewarding process to place greater emphasis on visual input. Empirical results demonstrate that CSR enhances performance and reduces hallucinations across ten benchmarks and tasks, achieving substantial improvements over existing methods by 7.62%. Our empirical results are further supported by rigorous theoretical analysis, under mild assumptions, verifying the effectiveness of introducing visual constraints into the self-rewarding paradigm. Additionally, CSR shows compatibility with different vision-language models and the ability to incrementally improve performance through iterative fine-tuning. Our data and code are available at https://github.com/YiyangZhou/CSR.
Forward citations
Cited by 13 Pith papers
-
Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Groc-PO applies preference optimization at three grounded stages — object grounding, contextual grounding, grounded reasoning — and outperforms final-answer-only DPO on hallucination and complex-reasoning benchmarks.
-
Improving Large Vision and Language Models by Learning from a Panel of Peers
A panel of LVLMs that generate, evaluate, and learn from each other's outputs improves average benchmark scores by 9 points across 15 tasks.
-
Controlling Multimodal LLMs via Reward-guided Decoding
MRGD guides MLLM decoding with a learned hallucination reward and a detector-based recall reward, allowing users to trade off object precision, recall, and test-time compute while reducing object hallucinations on CHA...
-
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?
Introduces GLIMPSE, a video-QA benchmark whose questions cannot be answered from single frames; best model GPT-o3 scores 66.43% vs 94.82% human accuracy.
-
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
A verifiable RL proxy task that asks VLMs to locate a single injected hallucination in a 200-word caption improves visual perception and transfers to math and abstract reasoning benchmarks.
-
Mitigating Object Hallucination via Robust Local Perception Search
A training-free decoding method that uses an MLLM's own local object descriptions as a reward prior, combined with CLIP similarity, to cut object hallucination, especially under adversarial image noise.
-
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models
HSCR uses visual token dropout and logit contrast to construct self-generated dispreferred answers, then trains a medical VLM with explicit and implicit preference losses, improving zero-shot Rad-VQA, SLAKE, and PathV...
-
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.
-
From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
Answer-oriented chain-of-thought prompts that generate both positive and negative reasoning data, combined with iterative DPO, improve multimodal LLM reasoning on several benchmarks.
-
Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
A two-stage, value-guided decoding strategy with a margin-based reward adjustment is claimed to yield more faithful, detailed VLM captions at about a quarter of VisVM's inference cost.
-
MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models
MCA-LLaVA reindexes image tokens by sums of mirrored 2D coordinates so instruction tokens attend across the whole image, reducing hallucination on POPE, CHAIR, and MME.
-
LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs
LeanPO improves Video-LLM alignment by using a reference-free average-likelihood reward, self-generated winning/losing pairs, and dynamic label smoothing, yielding gains on six video benchmarks.
-
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning
ASPO's adaptive sentence-level loss, by the paper's own definitions, reduces exactly to the standard DPO loss, leaving no difference in the optimization objective.
Discussion (0). Sign in to comment.