arXiv Computer Vision By Yuxia Qiao, Xinhao Zhong, Junhao Li, Yi Sun, Jiaxin Hong, Shuoyang Sun, Bin Chen

InfiHall-Bench: A Benchmark for Hallucination Evaluation in Autoregressive Text-to-Image Generation

Read the original on arXiv Computer Vision →

InfiHall-Bench is a new benchmark for evaluating hallucinations in visual autoregressive (VAR) text-to-image models, comprising 411 prompts that systematically combine five core visual skills—attribute binding, spatial relation, action relation, part consistency, and scene consistency. The benchmark reveals that VAR models exhibit persistent hallucinations across different autoregressive scales, prompting the authors to propose Confidence-Masked Hallucination Mitigation (CMHM), which focuses training on uncertain predictions and outperforms standard LoRA fine-tuning. InfiHall-Bench also demonstrates greater diagnostic power than existing diffusion-focused benchmarks by distinguishing models that appear comparable under current compositional tests.

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 Computer Vision.

arXiv Computer Vision
Nov 5

DreamRealm: Exploring and Materializing Hallucination Worlds for Trustworthy Vision-Language Models

arXiv:2611.06433v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post...

By Benlei Cui, Chunyang Chai, Yiliang Zhang, Xiaoqian Xia, Chengwen Yao, Song Li, Longtao Huang, Yuwen Zhai, Haiwen Hong
arXiv Computation and Language
Aug 27

Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models

In 2026, the SHROOM-Visions shared task was launched at the UncertaiNLP Workshop co‑located with EMNLP to address hallucinations in large vision‑language models. The task builds on the SHEEP dataset and asks participants to detect and classify fine‑grained hallucination spans in image‑conditioned text generation across four languages (Chinese, English, French, Italian) using a five‑class taxonomy. The competition attracted 27 teams and over 600 system submissions, with top systems achieving character‑level, label‑conditioned, and IoU scores of 0.58, 0.46, and 0.51 respectively, surpassing baselines by 30‑40 points.

By Ra\'ul V\'azquez, Aman Sinha, Chuyuan Li, Claudio Savelli, Eduardo Cal\`o, Emilio Raimond, Stella Frank, Hengyu Luo, Flavio Giobergia, Vincent Segonne, Lorenzo Vaiani, J\"org Tiedemann, Timothee Mickus