Timezone: »
Pretrained language models (LMs) perform well on many tasks even when learning from a few examples, but prior work uses many held-out examples to tune various aspects of learning, such as hyperparameters, training objectives, and natural language templates ("prompts"). Here, we evaluate the few-shot ability of LMs when such held-out examples are unavailable, a setting we call true few-shot learning. We test two model selection criteria, cross-validation and minimum description length, for choosing LM prompts and hyperparameters in the true few-shot setting. On average, both marginally outperform random selection and greatly underperform selection based on held-out examples. Moreover, selection criteria often prefer models that perform significantly worse than randomly-selected ones. We find similar results even when taking into account our uncertainty in a model's true performance during selection, as well as when varying the amount of computation and number of examples used for selection. Overall, our findings suggest that prior work significantly overestimated the true few-shot ability of LMs given the difficulty of few-shot model selection.
Author Information
Ethan Perez (New York University)
My research focuses on developing question-answering methods that generalize to harder questions than we have supervision for. Learning from human examples (supervised learning) won't scale to these kinds of questions, so I am investigating other paradigms that recursively break down harder questions into simpler ones.
Douwe Kiela (Facebook AI Research)
Kyunghyun Cho (Genentech | New York University)
More from the Same Authors
-
2021 : NaturalProofs: Mathematical Theorem Proving in Natural Language »
Sean Welleck · Jiacheng Liu · Ronan Le Bras · Hanna Hajishirzi · Yejin Choi · Kyunghyun Cho -
2021 : KLUE: Korean Language Understanding Evaluation »
Sungjoon Park · Jihyung Moon · Sungdong Kim · Won Ik Cho · Ji Yoon Han · Jangwon Park · Chisung Song · Junseong Kim · Youngsook Song · Taehwan Oh · Joohong Lee · Juhyun Oh · Sungwon Lyu · Younghoon Jeong · Inkwon Lee · Sangwoo Seo · Dongjun Lee · Hyunwoo Kim · Myeonghwa Lee · Seongbo Jang · Seungwon Do · Sunkyoung Kim · Kyungtae Lim · Jongwon Lee · Kyumin Park · Jamin Shin · Seonghyun Kim · Lucy Park · Alice Oh · Jung-Woo Ha · Kyunghyun Cho -
2021 : Function-guided protein design by deep manifold sampling »
Vladimir Gligorijevic · Stephen Ra · Dan Berenberg · Richard Bonneau · Kyunghyun Cho -
2021 : Facebook - Data Centric Infrastructure »
Douwe Kiela -
2021 : Function-guided protein design by deep manifold sampling »
Vladimir Gligorijevic · Stephen Ra · Dan Berenberg · Richard Bonneau · Kyunghyun Cho -
2021 : Invited talk - Douwe Kiela »
Douwe Kiela -
2021 Poster: Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking »
Zhiyi Ma · Kawin Ethayarajh · Tristan Thrush · Somya Jain · Ledell Wu · Robin Jia · Christopher Potts · Adina Williams · Douwe Kiela -
2021 : Introduction Competion Day 1 »
Douwe Kiela -
2021 Poster: Human-Adversarial Visual Question Answering »
Sasha Sheng · Amanpreet Singh · Vedanuj Goswami · Jose Magana · Tristan Thrush · Wojciech Galuba · Devi Parikh · Douwe Kiela -
2020 : Q & A and Panel Session with Dan Weld, Kristen Grauman, Scott Yih, Emma Brunskill, and Alex Ratner »
Kristen Grauman · Wen-tau Yih · Alexander Ratner · Emma Brunskill · Douwe Kiela · Daniel S. Weld -
2020 Workshop: HAMLETS: Human And Model in the Loop Evaluation and Training Strategies »
Divyansh Kaushik · Bhargavi Paranjape · Forough Arabshahi · Yanai Elazar · Yixin Nie · Max Bartolo · Polina Kirichenko · Pontus Lars Erik Saito Stenetorp · Mohit Bansal · Zachary Lipton · Douwe Kiela -
2020 : Opening Remarks »
Divyansh Kaushik · Bhargavi Paranjape · Douwe Kiela -
2020 : The Hateful Memes Challenge: Live award ceremony and winner presentations »
Douwe Kiela -
2020 : The Hateful Memes Challenge: Competition Overview »
Douwe Kiela -
2020 Poster: The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes »
Douwe Kiela · Hamed Firooz · Aravind Mohan · Vedanuj Goswami · Amanpreet Singh · Pratik Ringshia · Davide Testuggine -
2020 Poster: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks »
Patrick Lewis · Ethan Perez · Aleksandra Piktus · Fabio Petroni · Vladimir Karpukhin · Naman Goyal · Heinrich Küttler · Mike Lewis · Wen-tau Yih · Tim Rocktäschel · Sebastian Riedel · Douwe Kiela -
2020 Poster: Learning Optimal Representations with the Decodable Information Bottleneck »
Yann Dubois · Douwe Kiela · David Schwab · Ramakrishna Vedantam -
2020 Spotlight: Learning Optimal Representations with the Decodable Information Bottleneck »
Yann Dubois · Douwe Kiela · David Schwab · Ramakrishna Vedantam -
2019 : Audrey Durand, Douwe Kiela, Kamalika Chaudhuri moderated by Yann Dauphin »
Audrey Durand · Kamalika Chaudhuri · Yann Dauphin · Orhan Firat · Dilan Gorur · Douwe Kiela -
2019 : Douwe Kiela - Benchmarking Progress in AI: A New Benchmark for Natural Language Understanding »
Douwe Kiela -
2019 Workshop: Emergent Communication: Towards Natural Language »
Abhinav Gupta · Michael Noukhovitch · Cinjon Resnick · Natasha Jaques · Angelos Filos · Marie Ossenkopf · Angeliki Lazaridou · Jakob Foerster · Ryan Lowe · Douwe Kiela · Kyunghyun Cho -
2019 Poster: Hyperbolic Graph Neural Networks »
Qi Liu · Maximilian Nickel · Douwe Kiela -
2018 Workshop: Emergent Communication Workshop »
Jakob Foerster · Angeliki Lazaridou · Ryan Lowe · Igor Mordatch · Douwe Kiela · Kyunghyun Cho -
2018 : Panel Discussion »
Antonio Torralba · Douwe Kiela · Barbara Landau · Angeliki Lazaridou · Joyce Chai · Christopher Manning · Stevan Harnad · Roozbeh Mottaghi -
2018 : Douwe Kiela - Learning Multimodal Embeddings »
Douwe Kiela -
2018 Workshop: Visually grounded interaction and language »
Florian Strub · Harm de Vries · Erik Wijmans · Samyak Datta · Ethan Perez · Mateusz Malinowski · Stefan Lee · Peter Anderson · Aaron Courville · Jeremie MARY · Dhruv Batra · Devi Parikh · Olivier Pietquin · Chiori HORI · Tim Marks · Anoop Cherian -
2017 Workshop: Emergent Communication Workshop »
Jakob Foerster · Igor Mordatch · Angeliki Lazaridou · Kyunghyun Cho · Douwe Kiela · Pieter Abbeel -
2017 Poster: Poincaré Embeddings for Learning Hierarchical Representations »
Maximilian Nickel · Douwe Kiela -
2017 Spotlight: Poincaré Embeddings for Learning Hierarchical Representations »
Maximilian Nickel · Douwe Kiela