On-the-Fly Attention Modulation for Neural Generation

v1v2 (latest)

On-the-Fly Attention Modulation for Neural Generation

Findings (Findings), 2021

2 January 2021

Chandra Bhagavatula

Antoine Bosselut

Jackie C.K. Cheung

Yejin Choi

ArXiv (abs)PDF HTML

Papers citing "On-the-Fly Attention Modulation for Neural Generation"

11 / 11 papers shown

Title
Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization Joonho Yang Seunghyun Yoon Hwan Chang Byeongjeong Kim Hwanhee Lee HILM 460 2 0 21 May 2025
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model ReasoningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 Guang Dai Lijie Hu Di Wang LRM 373 9 0 17 Feb 2025
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization Cheng-Yu Hsieh Yung-Sung Chuang Chun-Liang Li Zifeng Wang Long T. Le ... James R. Glass Alexander Ratner Zifeng Wang Ranjay Krishna Tomas Pfister 347 72 0 23 Jun 2024
DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation Chen Xu Tian Lan Changlong Yu Wei Wang Jun Gao ... Qunxi Dong Kun Qian Piji Li Wei Bi Bin Hu 372 2 0 04 Mar 2024
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Buse Giledereli Jiaoda Li Yu Fei Alessandro Stolfo Wangchunshu Zhou Guangtao Zeng Antoine Bosselut Mrinmaya Sachan LRM 377 59 0 23 Oct 2023
Dense Text-to-Image Generation with Attention ModulationIEEE International Conference on Computer Vision (ICCV), 2023 Yunji Kim Jiyoung Lee Jin-Hwa Kim Jung-Woo Ha Jun-Yan Zhu DiffM 269 181 0 24 Aug 2023
Should We Attend More or Less? Modulating Attention for Fairness A. Zayed Gonçalo Mordido Samira Shabanian Sarath Chandar 255 15 0 22 May 2023
On the Blind Spots of Model-Based Evaluation Metrics for Text GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Tianxing He Jingyu Zhang Tianle Wang Sachin Kumar Dong Wang James R. Glass Yulia Tsvetkov 379 59 0 20 Dec 2022
Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating AttentionConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Wenhao Li Xiaoyuan Yi Jinyi Hu Maosong Sun Xing Xie 223 2 0 14 Nov 2022
ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Yucheng Zhou Tao Shen Xiubo Geng Guodong Long Daxin Jiang 355 74 0 04 Mar 2022
Controlling the Focus of Pretrained Language Generation ModelsFindings (Findings), 2022 Jiabao Ji Yoon Kim James R. Glass Tianxing He 259 5 0 02 Mar 2022