paper-with-me

홈 › Papers

The Pitfalls of Defining Hallucination

2024-01-15 · Kees Van Deemter

Despite impressive advances in Natural Language Generation (NLG) and Large Language Models (LLMs), researchers are still unclear about important aspects of NLG evaluation. To substantiate this claim, I examine current classifications of hallucination and omission in Data-text NLG, and I propose a logic-based synthesis of these classfications. I conclude by highlighting some remaining limitations of all current thinking about hallucination and by discussing implications for LLMs.

📄 PDF Abstract BibTeX arXiv:2401.07897

Code (0)

등록된 구현이 없습니다.

Tasks

Hallucinationnlg evaluationText Generation

Similar Papers 제목 키워드 기반

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation

2025-09-25 · Seyed Amir Kasaei, Mohammad Hossein Rohban arxiv

In language and vision-language models, hallucination is broadly understood as content generated from a model's prior knowledge or biases rather than from the given input. While this phenomenon has been studied in those …

LPOI: Listwise Preference Optimization for Vision Language Models

2025-05-27 · Fatemeh Pesaran Zadeh, Yoojin Oh, Gunhee Kim

Aligning large VLMs with human preferences is a challenging task, as methods like RLHF and DPO often overfit to textual information or exacerbate hallucinations. Although augmenting negative image samples partially addre…

Object

A Unified Definition of Hallucination: It's The World Model, Stupid!

2025-12-25 · Emmy Liu, Varun Gangal, Chelsea Zou, Michael Yu 외 arxiv

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and f…

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

2026-05-26 · Xiaotian Ye, Xiaohan Wang, Mengqi Zhang, Shu Wu arxiv

Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fictitious knowledge in place of undesired content. However, in this wo…

VidHal: Benchmarking Temporal Hallucinations in Vision LLMs

2024-11-25 · Wey Yeh Choong, Yangyang Guo, Mohan Kankanhalli

Vision Large Language Models (VLLMs) are widely acknowledged to be prone to hallucination. Existing research addressing this problem has primarily been confined to image inputs, with limited exploration of video-based ha…

BenchmarkingHallucination