Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer 0001, Kyle Chard, Ian T. Foster. Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models. In Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi, editors, Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2023, Singapore, December 7, 2023. pages 342-356, Association for Computational Linguistics, 2023. [doi]
@inproceedings{SakarvadiaAKGHBCF23, title = {Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models}, author = {Mansi Sakarvadia and Aswathy Ajith and Arham Khan and Daniel Grzenda and Nathaniel Hudson and André Bauer 0001 and Kyle Chard and Ian T. Foster}, year = {2023}, url = {https://aclanthology.org/2023.blackboxnlp-1.26}, researchr = {https://researchr.org/publication/SakarvadiaAKGHBCF23}, cites = {0}, citedby = {0}, pages = {342-356}, booktitle = {Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2023, Singapore, December 7, 2023}, editor = {Yonatan Belinkov and Sophie Hao and Jaap Jumelet and Najoung Kim and Arya McCarthy and Hosein Mohebbi}, publisher = {Association for Computational Linguistics}, isbn = {979-8-89176-052-3}, }