paper-with-me

홈 › Papers

Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection

2026-09-09 · Eli Schwartz arxiv

We present our system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. A small ($4$B-parameter) VLM is fine-tuned as a per-token classifier reading a two-token feature from its own hidden states, and is ensembled with a $\sim$400B zero-shot VLM judge at prediction time. Both components see off-the-shelf OCR of any visible in-image text. We use synthetic hallucination data generated by the large model as a source of ensemble diversity, and use validation to select feature layer, training data and OCR grounding. Our official entry reaches mean Cor $0.487$ / Cor-lbl $0.387$ on the hidden test set, placing $6$th/$28$ (EN), $6$th/$21$ (FR), $8$th/$21$ (IT) and $7$th/$22$ (ZH) on the task's primary Cor-lbl metric.

📄 PDF Abstract BibTeX arXiv:2609.10244

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EdgeJury: Cross-Reviewed Small-Model Ensembles for Truthful Question Answering on Serverless Edge Inference

2025-12-29 · Aayush Kumar arxiv

Hallucinations hinder reliable question answering, especially in resource-constrained deployments where frontier-scale models or retrieval pipelines may be impractical. We present EdgeJury, a lightweight ensemble framewo…

Question Answering

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

2025-10-10 · Hoigi Seo, Dong Un Kang, Hyunjin Cho, Joohoon Lee 외 arxiv

Large vision-language models (LVLMs), which integrate a vision encoder (VE) with a large language model, have achieved remarkable success across various tasks. However, there are still crucial challenges in LVLMs such as…

Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation

2026-02-02 · Seonghyeon Park, Jewon Yeom, Jaewon Sok, Jeongjae Park 외 arxiv

Quantifying uncertainty in Large Language Models (LLMs) is essential for mitigating hallucinations and enabling risk-aware deployment in safety-critical tasks. However, estimating Epistemic Uncertainty(EU) via Deep Ensem…

Knowledge Distillation

EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens

2025-03-10 · Liwei Che, Tony Qingze Liu, Jing Jia, Weiyi Qin 외

Despite their remarkable potential, Large Vision-Language Models (LVLMs) still face challenges with object hallucination, a problem where their generated outputs mistakenly incorporate objects that do not actually exist.…

HallucinationLanguage ModelingLanguage ModellingObject+1

Scalable Token-Level Hallucination Detection in Large Language Models

2026-05-12 · Rui Min, Tianyu Pang, Chao Du, Minhao Cheng 외 arxiv

Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are difficult to detect in reasoning-intensive tasks, where the content appea…

Domain Generalization