Simple Token-Level Confidence Improves Caption Correctness

11 May 2023

Papers citing "Simple Token-Level Confidence Improves Caption Correctness"

10 / 10 papers shown

Title
Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data Spencer Whitehead Jacob Phillips Sean Hendryx 16 0 0 30 Aug 2024
MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification Laura Fieback Jakob Spiegelberg Hanno Gottschalk MLLM 54 5 0 29 May 2024
Mitigating Open-Vocabulary Caption Hallucinations Assaf Ben-Kish Moran Yanuka Morris Alper Raja Giryes Hadar Averbuch-Elor MLLM VLM 11 6 0 06 Dec 2023
Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning Ali Furkan Biten L. G. I. Bigorda Dimosthenis Karatzas 87 55 0 04 Oct 2021
How Much Can CLIP Benefit Vision-and-Language Tasks? Sheng Shen Liunian Harold Li Hao Tan Mohit Bansal Anna Rohrbach Kai-Wei Chang Z. Yao Kurt Keutzer CLIP VLM MLLM 185 403 0 13 Jul 2021
Unifying Vision-and-Language Tasks via Text Generation Jaemin Cho Jie Lei Hao Tan Mohit Bansal MLLM 249 518 0 04 Feb 2021
Reducing conversational agents' overconfidence through linguistic calibration Sabrina J. Mielke Arthur Szlam Emily Dinan Y-Lan Boureau 203 152 0 30 Dec 2020
Calibration of Pre-trained Transformers Shrey Desai Greg Durrett UQLM 237 288 0 17 Mar 2020
Show, Edit and Tell: A Framework for Editing Image Captions Fawaz Sammani Luke Melas-Kyriazi KELM DiffM 43 59 0 06 Mar 2020
Neural Baby Talk Jiasen Lu Jianwei Yang Dhruv Batra Devi Parikh VLM 189 432 0 27 Mar 2018