paper-with-me

홈 › Papers

MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models

2024-04-10 · Rahul Mehta, Andrew Hoblitzell, Jack O'Keefe, Hyeju Jang, Vasudeva Varma

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. This paper describes our winning solution ranked 1st and 2nd in the 2 sub-tasks of model agnostic and model aware tracks respectively. We propose a meta-regressor framework of LLMs for model evaluation and integration that achieves the highest scores on the leaderboard. We also experiment with various transformer-based models and black box methods like ChatGPT, Vectara, and others. In addition, we perform an error analysis comparing GPT4 against our best model which shows the limitations of the former.

📄 PDF Abstract BibTeX arXiv:2404.06948

Code (0)

등록된 구현이 없습니다.

Tasks

Hallucination

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?

2026-01-17 · Xu Hu, Yifan Zhang, Songtao Wei, Chen Zhao 외 arxiv

Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tun…

parameter-efficient fine-tuning

Do LLM hallucination detectors suffer from low-resource effect?

2026-01-23 · Debtanu Datta, Mohan Kishore Chilukuri, Yash Kumar, Saptarshi Ghosh 외 arxiv

LLMs, while outperforming humans in a wide range of tasks, can still fail in unanticipated ways. We focus on two pervasive failure modes: (i) hallucinations, where models produce incorrect information about the world, an…

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models

2026-01-19 · Nay Myat Min, Long H. Pham, Hongyu Zhang, Jun Sun arxiv

Single-pass hallucination detectors rely on internal telemetry (e.g., uncertainty, hidden-state geometry, and attention) of large language models, implicitly assuming hallucinations leave separable traces in these signal…

DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning

2026-03-17 · Yanyu Qian, Yue Tan, Yixin Liu, Wang Yu 외 arxiv

Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders thei…

EnsemHalDet: Robust VLM Hallucination Detection via Ensemble of Internal State Detectors

2026-04-03 · Ryuhei Miyazato, Shunsuke Kitada, Kei Harada arxiv

Vision-Language Models (VLMs) excel at multimodal tasks, but they remain vulnerable to hallucinations that are factually incorrect or ungrounded in the input image. Recent work suggests that hallucination detection using…

Ensemble Learning