SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully

v1v2v3 (latest)

SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

11 January 2024

ArXiv (abs)PDF HTML

Papers citing "SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully"

10 / 10 papers shown

Title
Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts Raavi Gupta Pranav Hari Panicker S. Bhatia Ganesh Ramakrishnan HILM 96 0 0 15 Nov 2025
MLP Memory: A Retriever-Pretrained Memory for Large Language Models Rubin Wei Jiaqi Cao Jiarui Wang Jushi Kai Qipeng Guo Bowen Zhou Zhouhan Lin RALM 205 0 0 03 Aug 2025
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers Jingze Zhu Y. Wu Wenbo Zhu Jiawang Cao Y. Zheng Jiawei Chen Xu Yang Bernt Schiele Jonas Fischer Xinting Hu OffRL 162 0 0 06 Jul 2025
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation Dingwei Chen Ziqiang Liu Feiteng Fang Chak Tou Leong Shiwen Ni A. Argha Hamid Alinejad-Rokny Min Yang Chengming Li KELM HILM 173 2 0 03 Jun 2025
Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful ComparatorsAAAI Conference on Artificial Intelligence (AAAI), 2024 Jinjie Wei Dongling Xiao Jinjie Wei Mingcheng Li Zhaoyu Chen Ke Li Li Zhang HILM 463 14 0 28 Jan 2025
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination DetectionNeural Information Processing Systems (NeurIPS), 2024 Xuefeng Du Chaowei Xiao Yixuan Li HILM 220 56 0 26 Sep 2024
Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs Shiping Liu Kecheng Zheng Wei Chen MLLM 217 106 0 31 Jul 2024
Mitigating Large Language Model Hallucination with Faithful Finetuning Minda Hu Bowei He Yufei Wang Liangyou Li Chen Ma Irwin King HILM 251 20 0 17 Jun 2024
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space Shaolei Zhang Tian Yu Yang Feng HILM KELM 247 78 0 27 Feb 2024
Generating Benchmarks for Factuality Evaluation of Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 Dor Muhlgay Ori Ram Inbal Magar Yoav Levine Nir Ratner Yonatan Belinkov Omri Abend Kevin Leyton-Brown Amnon Shashua Y. Shoham HILM 183 122 0 13 Jul 2023