b'Jacob Andreas'

research

∙ 09/07/2023

A Function Interpretation Benchmark for Evaluating Interpretability Methods

Labeling neural network submodules with human-legible descriptions is us...

0 Sarah Schwettmann, et al. ∙

research

∙ 08/17/2023

Linearity of Relation Decoding in Transformer Language Models

Much of the knowledge encoded in transformer language models (LMs) may b...

0 Evan Hernandez, et al. ∙

research

∙ 06/30/2023

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

Do neural networks, trained on well-understood algorithmic tasks, reliab...

0 Ziqian Zhong, et al. ∙

research

∙ 06/22/2023

From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought

How does language inform our downstream thinking? In particular, how do ...

0 Lionel Wong, et al. ∙

research

∙ 05/31/2023

Decision-Oriented Dialogue for Human-AI Collaboration

We describe a class of tasks called decision-oriented dialogues, in whic...

0 Jessy Lin, et al. ∙

research

∙ 05/15/2023

Natural Language Decomposition and Interpretation of Complex Utterances

Natural language interfaces often require supervised data to translate u...

2 Harsh Jhamtani, et al. ∙

research

∙ 04/03/2023

Measuring and Manipulating Knowledge Representations in Language Models

Neural language models (LMs) represent facts about the world described b...

0 Evan Hernandez, et al. ∙

research

∙ 03/28/2023

Language Models Trained on Media Diets Can Predict Public Opinion

Public opinion reflects and shapes societal behavior, but the traditiona...

0 Eric Chu, et al. ∙

research

∙ 02/13/2023

Guiding Pretraining in Reinforcement Learning with Large Language Models

Reinforcement learning algorithms typically struggle in the absence of a...

0 Yuqing Du, et al. ∙

research

∙ 02/03/2023

LaMPP: Language Models as Probabilistic Priors for Perception and Action

Language models trained on large text corpora encode rich distributional...

0 Belinda Z. Li, et al. ∙

research

∙ 12/20/2022

Language Modeling with Latent Situations

Language models (LMs) often generate incoherent outputs: they refer to e...

0 Belinda Z. Li, et al. ∙

research

∙ 12/03/2022

Language Models as Agent Models

Language models (LMs) are trained on collections of documents, written b...

0 Jacob Andreas, et al. ∙

research

∙ 11/28/2022

What learning algorithm is in-context learning? Investigations with linear models

Neural sequence models, especially transformers, exhibit a remarkable ca...

0 Ekin Akyürek, et al. ∙

research

∙ 11/15/2022

Hierarchical Phrase-based Sequence-to-Sequence Learning

We describe a neural transducer that maintains the flexibility of standa...

0 Bailin Wang, et al. ∙

research

∙ 11/02/2022

Characterizing Intrinsic Compositionality in Transformers with Tree Projections

When trained on language data, do transformers learn some arbitrary comp...

0 Shikhar Murty, et al. ∙

research

∙ 10/20/2022

ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications

We introduce ObSynth, an interactive system leveraging the domain knowle...

0 Alex Gu, et al. ∙

research

∙ 09/16/2022

The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding

In a real-world dialogue system, generated responses must satisfy severa...

10 Hao Fang, et al. ∙

research

∙ 05/23/2022

Tracing Knowledge in Language Models Back to the Training Data

Neural language models (LMs) have been shown to memorize a great deal of...

0 Ekin Akyürek, et al. ∙

research

∙ 05/11/2022

Identifying concept libraries from language about object structure

Our understanding of the visual world goes beyond naming objects, encomp...

7 Catherine Wong, et al. ∙

research

∙ 04/11/2022

Correcting Robot Plans with Natural Language Feedback

When humans design cost or goal specifications for robots, they often pr...

2 Pratyusha Sharma, et al. ∙

research

∙ 03/19/2022

Teachable Reinforcement Learning via Advice Distillation

Training automated agents to complete complex tasks in interactive envir...

0 Olivia Watkins, et al. ∙

research

∙ 02/03/2022

Pre-Trained Language Models for Interactive Decision-Making

Language model (LM) pre-training has proven useful for a wide variety of...

68 Shuang Li, et al. ∙

research

∙ 01/30/2022

Compositionality as Lexical Symmetry

Standard deep network models lack the inductive biases needed to general...

0 Ekin Akyürek, et al. ∙

research

∙ 01/26/2022

Natural Language Descriptions of Deep Visual Features

Some neurons in deep networks specialize in recognizing highly specific ...

2 Evan Hernandez, et al. ∙

research

∙ 12/14/2021

Modeling Strong and Human-Like Gameplay with KL-Regularized Search

We consider the task of building strong but human-like policies in multi...

0 Athul Paul Jacob, et al. ∙

research

∙ 12/06/2021

Quantifying Adaptability in Pre-trained Language Models with 500 Tasks

When a neural language model (LM) is adapted to perform a new task, what...

1 Belinda Z. Li, et al. ∙

research

∙ 11/04/2021

How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction

After a neural sequence model encounters an unexpected token, can its be...

0 Anthony Bau, et al. ∙

research

∙ 10/13/2021

Subspace Regularizers for Few-Shot Class Incremental Learning

Few-shot class incremental learning – the problem of updating a trained ...

0 Afra Feyza Akyürek, et al. ∙

research

∙ 10/08/2021

Toward a Visual Concept Vocabulary for GAN Latent Space

A large body of recent work has identified transformations in the latent...

11 Sarah Schwettmann, et al. ∙

research

∙ 10/04/2021

Skill Induction and Planning with Latent Language

We present a framework for learning hierarchical policies from demonstra...

0 Pratyusha Sharma, et al. ∙

research

∙ 06/18/2021

Leveraging Language to Learn Program Abstractions and Search Heuristics

Inductive program synthesis, or inferring programs from examples of desi...

63 Catherine Wong, et al. ∙

research

∙ 06/15/2021

What Context Features Can Transformer Language Models Use?

Transformer-based language models benefit from conditioning on contexts ...

0 Joe O'Connor, et al. ∙

research

∙ 06/07/2021

Lexicon Learning for Few-Shot Neural Sequence Modeling

Sequence-to-sequence transduction is the core problem in language proces...

0 Ekin Akyürek, et al. ∙

research

∙ 06/01/2021

Implicit Representations of Meaning in Neural Language Models

Does the effectiveness of neural language models derive entirely from ac...

0 Belinda Z. Li, et al. ∙

research

∙ 05/15/2021

The Low-Dimensional Linear Geometry of Contextualized Word Representations

Black-box probing models can reliably extract linguistic features like t...

0 Evan Hernandez, et al. ∙

research

∙ 04/17/2021

Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales

The past decade has witnessed a groundbreaking rise of machine learning ...

21 Jacob Andreas, et al. ∙

research

∙ 04/15/2021

Multitasking Inhibits Semantic Drift

When intelligent agents communicate to accomplish shared goals, how do t...

0 Athul Paul Jacob, et al. ∙

research

∙ 12/23/2020

Representing Partial Programs with Blended Abstract Semantics

Synthesizing programs from examples requires searching over a vast, comb...

3 Maxwell Nye, et al. ∙

research

∙ 10/08/2020

Learning to Recombine and Resample Data for Compositional Generalization

Flexible neural models outperform grammar- and automaton-based counterpa...

0 Ekin Akyürek, et al. ∙

research

∙ 09/24/2020

Task-Oriented Dialogue as Dataflow Synthesis

We describe an approach to task-oriented dialogue in which dialogue stat...

0 Jacob Andreas, et al. ∙

research

∙ 08/22/2020

Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment

We propose and demonstrate a novel machine learning algorithm that asses...

13 Geeticka Chauhan, et al. ∙

research

∙ 07/23/2020

Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction

We present a randomized controlled trial for a model-in-the-loop regress...

13 Eric Chu, et al. ∙

research

∙ 06/24/2020

Compositional Explanations of Neurons

We describe a procedure for explaining neurons in deep representations b...

28 Jesse Mu, et al. ∙

research

∙ 04/28/2020

Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data

Large, human-annotated datasets are central to the development of natura...

1 Alana Marzoev, et al. ∙

research

∙ 04/21/2020

Experience Grounds Language

Successful linguistic communication relies on a shared experience of the...

1 Yonatan Bisk, et al. ∙

research

∙ 03/11/2020

A Benchmark for Systematic Generalization in Grounded Language Understanding

Human language users easily interpret expressions that describe unfamili...

8 Laura Ruis, et al. ∙

research

∙ 06/10/2019

A Survey of Reinforcement Learning Informed by Natural Language

To be successful in real-world tasks, Reinforcement Learning (RL) needs ...

52 Jelena Luketina, et al. ∙

research

∙ 04/21/2019

Good-Enough Compositional Data Augmentation

We propose a simple data augmentation protocol aimed at providing a comp...

0 Jacob Andreas, et al. ∙

research

∙ 04/02/2019

Pragmatically Informative Text Generation

We improve the informativeness of models for conditional text generation...

0 Sheng Shen, et al. ∙

research

∙ 02/19/2019

Measuring Compositionality in Representation Learning

Many machine learning algorithms represent input data with vector embedd...

4 Jacob Andreas, et al. ∙

Jacob Andreas

Featured Co-authors