Profiles2020-2023
Matthew E Peters
Allen Institute for AI
Also published as Matthew Peters
11Papers
5Last author
24Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context LearningAuthor 3 of 5ACL 2023 · 5 citations
- HINT: Hypernetwork Instruction Tuning for Efficient Zero- and Few-Shot GeneralisationAuthor 5 of 5ACL 2023 · 1 citation
- Tailor: Generating and Perturbing Text with Semantic ControlsAuthor 4 of 5ACL 2022 · 85 citations
- ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft PromptsAuthor 3 of 5EMNLP 2022 · 55 citations
- Staged Training for Transformer Language ModelsAuthor 5 of 6ICML 2022 · 52 citations
- Extracting Latent Steering Vectors from Pretrained Language ModelsAuthor 3 of 3ACL Findings 2022 · 32 citations
- Hyperdecoders: Instance-specific decoders for multi-task NLPAuthor 2 of 2EMNLP Findings 2022 · 11 citations
- Does Self-Rationalization Improve Robustness to Spurious Correlations?Author 2 of 3EMNLP 2022 · 4 citations
- Explaining NLP Models via Minimal Contrastive Editing (MiCE)Author 3 of 3ACL Findings 2021 · 86 citations
- CDLM: Cross-Document Language ModelingAuthor 4 of 6EMNLP Findings 2021 · 56 citations
- Learning from Task DescriptionsAuthor 4 of 4EMNLP 2020 · 4 citations
