arXiv AI July 16, 2026 By Zhixiao Zheng, Zheren Fu, Zhiyuan Yao, Chunxiao Liu, Dongming Zhang, Zhendong Mao

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

arXiv:2607. 13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, content fabrication, and unfaithful reasoning, which substantially undermine their faithfulness and practical utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 12

Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language Models

arXiv:2605. 16411v3 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling.

By Qinwu Xu

llms computer-vision reinforcement-learning multimodal benchmarks safety

arXiv AI

Aug 7

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

arXiv:2605. 16411v2 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling.

By Qinwu Xu

llms computer-vision reinforcement-learning multimodal benchmarks safety

arXiv AI

3d ago

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...

By Zhihan Zhang, Lizi Liao

llms reinforcement-learning multimodal benchmarks

arXiv Computer Vision

Sep 21

DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

arXiv:2609.21675v1 Announce Type: new Abstract: Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural...

By Wan Xu, Yuanfan Guo, Kevin Han, LaLa Chen, Wangmeng Zuo

llms reinforcement-learning multimodal benchmarks safety

arXiv Computation and Language

Aug 31

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations

The paper introduces Cognitive Chain-of-Thought (CoCoT), a structured reasoning framework for vision‑language models that divides multimodal social reasoning into three cognitively inspired stages: Perception, Situation, and Norm. CoCoT improves performance across diverse tasks—multimodal intent disambiguation, theory of mind, social commonsense reasoning, and safety instruction following—by 5.9% to 4.6% on average. Fine‑tuning on CoCoT‑structured traces further boosts accuracy by 5–6% without explicit prompting, indicating that models internalize the structured reasoning pattern and that the approach enhances interpretability and social alignment in multimodal systems.

By Eunkyu Park, Wesley Hanwen Deng, Gunhee Kim, Motahhare Eslami, Maarten Sap

llms agents fine-tuning multimodal safety

arXiv AI

Jul 21

Constraint-Anchored Reasoning Traces

arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.

By Zehua Cheng, Wei Dai, Jiahao Sun

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language Models

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations

Constraint-Anchored Reasoning Traces