Contrastive Error Attribution for Finetuned Language Models

Contrastive Error Attribution for Finetuned Language Models

21 December 2022

Esin Durmus

Tatsunori Hashimoto

Papers citing "Contrastive Error Attribution for Finetuned Language Models"

10 / 10 papers shown

Title
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc Aleksander Madry TDI 82 136 0 01 Feb 2022
SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets Ann Yuan Daphne Ippolito Vitaly Nikolaev Chris Callison-Burch Andy Coenen Sebastian Gehrmann SyDa 121 21 0 11 Nov 2021
Entity-level Factual Consistency of Abstractive Text Summarization Feng Nan Ramesh Nallapati Zhiguo Wang Cicero Nogueira dos Santos Henghui Zhu Dejiao Zhang Kathleen McKeown Bing Xiang HILM 147 159 0 18 Feb 2021
Explaining and Improving Model Behavior with k Nearest Neighbor Representations Nazneen Rajani Ben Krause Wengpeng Yin Tong Niu R. Socher Caiming Xiong FAtt 23 33 0 18 Oct 2020
Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization Beliz Gunel Chenguang Zhu Michael Zeng Xuedong Huang HILM 29 42 0 27 Jun 2020
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions Xiaochuang Han Byron C. Wallace Yulia Tsvetkov MILM FAtt AAML TDI 28 167 0 14 May 2020
Semantic Noise Matters for Neural Natural Language Generation Ondrej Dusek David M. Howcroft Verena Rieser 47 118 0 10 Nov 2019
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization Shashi Narayan Shay B. Cohen Mirella Lapata AILaw 85 1,652 0 27 Aug 2018
The E2E Dataset: New Challenges For End-to-End Generation Jekaterina Novikova Ondrej Dusek Verena Rieser 64 456 0 28 Jun 2017
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 95 2,854 0 14 Mar 2017