arXiv AI
When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
3d ago
It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
arXiv:2609.37863v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model r...
arXiv AI
1d ago
VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision
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.
arXiv AI
Aug 26
Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally Grounded Tasks
The paper introduces a dual‑judge evaluation protocol for vision‑language models in legally grounded tasks, pairing a 0‑10 quality judge with a strict binary semantic‑equivalence judge. Using a controlled UK traffic‑sign interpretation task, the authors analyze 4,680 evaluations across visibility and occlusion conditions, finding moderate association between judges and an asymmetric Type II error pattern that is most pronounced under heavy occlusion. The protocol requires only one additional LLM call and reveals quality‑trustworthiness signals that single‑judge methods miss.
arXiv Computation and Language
Sep 21
JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems
JudgeSense is a benchmark comprising 880 items from human‑labelled corpora, each presented under two differently worded instructions that ask the same question. The study evaluates 25 judges from six providers across four tasks, measuring how rewording affects agreement with the judge’s own verdicts. Results show that rewording reduces agreement on all tasks, with significant effects on two, and that stability varies across tasks and is not predicted by parameter count.
arXiv AI
3d ago
JudgeProfile: Understanding and Steering Subjectivity in LLM Judges
JudgeProfile is a framework that analyzes the subjectivity of large language model (LLM) judges by separating evaluation into perception—how judges compare responses on attributes such as clarity, correctness, and detail—and prioritization—how much each attribute influences the final decision. Using the curated SubjectiveSet dataset of 50,013 response pairs evaluated by 21 judges across 87 attributes, the study finds that judges often agree on attribute judgments even when their overall choices differ. By estimating and adjusting attribute weights, the authors improve agreement with reference labels from 66.48% to 71.97%, outperforming fine‑tuning and rubric prompting.
arXiv AI
1d ago
The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating
The paper demonstrates that reading a large language model (LLM) judge’s verdict from the logits of its first generated token—an approach used in constrained decoding and likelihood‑scoring evaluation—introduces a significant distortion in position bias. Because judges do not always start with a verdict token (12–49% of cases for Qwen3 judges and <3% for Llama‑3.1‑8B and Phi‑3.5‑mini), this readout often returns the first response rather than a true judgment, inflating position bias by up to 42 points while barely affecting judge accuracy. The authors recommend reporting the frequency with which a judge leads with a verdict token to provide a more accurate assessment of position bias.