1 code implementation • 6 Apr 2024 • Yann Dubois, Balázs Galambosi, Percy Liang, Tatsunori B. Hashimoto
Even simple, known confounders such as preference for longer outputs remain in existing automated evaluation metrics.
no code implementations • 1 Dec 2023 • Jiayi Li, Rohan Taori, Tatsunori B. Hashimoto
Active learning aims to enhance model performance by strategically labeling informative data points.
1 code implementation • 26 Oct 2023 • Yonatan Oren, Nicole Meister, Niladri Chatterji, Faisal Ladhak, Tatsunori B. Hashimoto
In contrast, the tendency for language models to memorize example order means that a contaminated language model will find certain canonical orderings to be much more likely than others.
no code implementations • 7 Jul 2023 • Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma
Then, we find that changing the distribution of the covariates and weight vector to a non-isotropic Gaussian distribution has a strong impact on the learned algorithm: the global minimizer of the pre-training loss now implements a single step of $\textit{pre-conditioned}$ GD.
2 code implementations • NeurIPS 2023 • Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto
As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% improvement in win-rate against Davinci003.
1 code implementation • 31 Jan 2023 • Tianyi Zhang, Faisal Ladhak, Esin Durmus, Percy Liang, Kathleen McKeown, Tatsunori B. Hashimoto
Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood.
1 code implementation • 29 Nov 2022 • Tianyi Zhang, Tao Yu, Tatsunori B. Hashimoto, Mike Lewis, Wen-tau Yih, Daniel Fried, Sida I. Wang
Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions.
Ranked #23 on Code Generation on MBPP
1 code implementation • 8 Sep 2022 • Rohan Taori, Tatsunori B. Hashimoto
Datasets scraped from the internet have been critical to the successes of large-scale machine learning.
1 code implementation • 27 May 2022 • Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto
Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation.
1 code implementation • 23 May 2022 • Tianyi Zhang, Mina Lee, Lisa Li, Ende Shen, Tatsunori B. Hashimoto
While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content.
no code implementations • NAACL 2021 • Shikhar Murty, Tatsunori B. Hashimoto, Christopher Manning
Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training.
1 code implementation • ICLR 2020 • Shiori Sagawa*, Pang Wei Koh*, Tatsunori B. Hashimoto, Percy Liang
Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups.
8 code implementations • 20 Nov 2019 • Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy Liang
Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups.
Ranked #1 on Out-of-Distribution Generalization on UrbanCars
1 code implementation • 16 Nov 2019 • Mina Lee, Tatsunori B. Hashimoto, Percy Liang
We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game.
1 code implementation • IJCNLP 2019 • Yonatan Oren, Shiori Sagawa, Tatsunori B. Hashimoto, Percy Liang
Language models are generally trained on data spanning a wide range of topics (e. g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e. g., restaurant reviews).
2 code implementations • NAACL 2019 • Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang
How can we measure whether a natural language generation system produces both high quality and diverse outputs?
1 code implementation • NeurIPS 2018 • Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang
For the task of generating complex outputs such as source code, editing existing outputs can be easier than generating complex outputs from scratch.
1 code implementation • ICML 2018 • Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang
Machine learning models (e. g., speech recognizers) are usually trained to minimize average loss, which results in representation disparity---minority groups (e. g., non-native speakers) contribute less to the training objective and thus tend to suffer higher loss.
1 code implementation • 11 Apr 2018 • Tatsunori B. Hashimoto, Steve Yadlowsky, John C. Duchi
We develop an algorithm for minimizing a function using $n$ batched function value measurements at each of $T$ rounds by using classifiers to identify a function's sublevel set.
1 code implementation • NeurIPS 2017 • Tatsunori B. Hashimoto, John C. Duchi, Percy Liang
Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait.
3 code implementations • TACL 2018 • Kelvin Guu, Tatsunori B. Hashimoto, Yonatan Oren, Percy Liang
We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence.
no code implementations • TACL 2016 • Tatsunori B. Hashimoto, David Alvarez-Melis, Tommi S. Jaakkola
Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood.
no code implementations • NeurIPS 2015 • Tatsunori B. Hashimoto, Yi Sun, Tommi S. Jaakkola
Using these techniques we generalize results on the degeneracy of hitting times and analyze a metric based on the Laplace transformed hitting time (LTHT).
no code implementations • 18 Sep 2015 • Tatsunori B. Hashimoto, David Alvarez-Melis, Tommi S. Jaakkola
Continuous vector representations of words and objects appear to carry surprisingly rich semantic content.
no code implementations • 20 Nov 2014 • Tatsunori B. Hashimoto, Yi Sun, Tommi S. Jaakkola
We demonstrate empirically that the estimator performs well on simulated examples as well as on real-world co-purchasing graphs even with a small number of points and degree scaling as low as $\log(n)$.