The paper argues that multimodal large language models can answer vision benchmarks using only linguistic cues, revealing non-visual shortcuts. It proposes a Test‑set Stress‑Test (TsT) that trains a text‑only model on the test set to expose exploitable patterns, and introduces Iterative Bias Pruning (IBP) to remove high‑bias questions. Applying these methods to VSI‑Bench, CV‑Bench, and MMMU shows significant gaps between blind and vision‑aware performance and demonstrates that debiased benchmarks can reduce blind scores while preserving vision scores.
By Ellis Brown, Jihan Yang, Shusheng Yang, Rob Fergus, Saining Xie
arXiv:2605.14040v2 Announce Type: replace
Abstract: Trackable improvement in multimodal physics reasoning rests on a training-and-evaluation system that is itself rarely verified: the corpora a model...
By Shan Yang
The paper investigates whether panels of vision‑language models (VLMs) can reliably judge image aesthetics. It shows that a panel of holistic judges rarely outperforms its best member, but when each model scores images on five rubric‑defined dimensions and these dimension scores are fused across model families, the panel consistently beats the best single VLM on two datasets (EVA and PARA). The study demonstrates that the value of a panel depends on the type of input it receives, and that dimension‑based fusion yields measurable gains at the cost of additional labeling and API usage.
By Amit Jadhav, Shaurya Beriwala, Beomjin Kim
The study analyzes 373,019 judgments from LLM‑scored benchmarks, decomposing variance into system, item, judge, and interaction components via generalizability theory. It finds that with a single judge, generalizability converges to a ceiling determined by the system‑by‑judge variance, which is substantially lower in pairwise preference settings, allowing one judge to suffice. The research also reveals significant biases in presentation order and highlights that many published win‑rate claims fall below the measured floor of the benchmarks.
By Atul Anand
A 0.6B language model consistently answers YES to 1,200 logical tests, yet its behavior shows no discrimination. Linear probes reveal the correct verdict with high AUC (0.96) and transfer to unseen structures, but a single scalar readout fails due to a saturated decision threshold offset by +4.6 σ. Adjusting this threshold restores behavior accuracy from 50 % to 81 % and improves higher‑scale models, demonstrating that miscalibrated readouts, not hidden knowledge loss, drive performance gaps.
By Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
arXiv:2606. 11477v1 Announce Type: cross Abstract: Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats.
By Hartwig Grabowski
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.
By Zhelun Wu
arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.
By Bojie Li, Noah Shi
arXiv:2610.00111v1 Announce Type: new
Abstract: Model judges now supervise multimodal systems at scale, filtering training data, selecting outputs, and supplying the reward that shapes multimodal rea...
By Rasul Khanbayov, Hasan Kurban
arXiv:2610.17747v1 Announce Type: cross
Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step agai...
By Tianyang Xu, Jing Gao
VisionQ is a new benchmark for qualitative analysis in computer vision that evaluates vision‑language models (VLMs) on criterion‑conditioned visual discrimination. It is built from over 1,800 peer‑reviewed comparison figures in CVPR and ICCV papers, linking each image crop to author‑stated visual claims through 3,911 hand‑annotated data points. The benchmark includes a 51‑leaf taxonomy of visual criteria, a protocol that hides method identities and reports accuracy per criterion, and a DPO‑tuned Gemma‑4‑E4B judge that improves accuracy on a held‑out test set.
By Vu Dinh Xuan, Duc-Hai Nguyen, Minh-Dung Dao, Vu Quynh Giao, Quang Hong Nguyen, Binh-Son Hua, Barry O'Sullivan, David Murphy, Hoang D. Nguyen
arXiv:2609.00654v1 Announce Type: new
Abstract: We describe the SciTrue team's participation in both subtasks of the NTCIR-19 SciClaimEval task~\cite{sciclaimeval}, which asks systems to verify scien...
By Qiming Bao, Ne\c{s}et \"Ozkan Tan, Siyuan Wang, Mark Gahegan