research
∙
09/07/2023
A Function Interpretation Benchmark for Evaluating Interpretability Methods
Labeling neural network submodules with human-legible descriptions is us...
share
research
∙
08/17/2023
Linearity of Relation Decoding in Transformer Language Models
Much of the knowledge encoded in transformer language models (LMs) may b...
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...
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 ...
research
∙
05/31/2023
Decision-Oriented Dialogue for Human-AI Collaboration
We describe a class of tasks called decision-oriented dialogues, in whic...
research
∙
05/15/2023
Natural Language Decomposition and Interpretation of Complex Utterances
Natural language interfaces often require supervised data to translate u...
research
∙
04/03/2023
Measuring and Manipulating Knowledge Representations in Language Models
Neural language models (LMs) represent facts about the world described b...
research
∙
03/28/2023
Language Models Trained on Media Diets Can Predict Public Opinion
Public opinion reflects and shapes societal behavior, but the traditiona...
research
∙
02/13/2023
Guiding Pretraining in Reinforcement Learning with Large Language Models
Reinforcement learning algorithms typically struggle in the absence of a...
research
∙
02/03/2023
LaMPP: Language Models as Probabilistic Priors for Perception and Action
Language models trained on large text corpora encode rich distributional...
research
∙
12/20/2022
Language Modeling with Latent Situations
Language models (LMs) often generate incoherent outputs: they refer to e...
research
∙
12/03/2022
Language Models as Agent Models
Language models (LMs) are trained on collections of documents, written b...
research
∙
11/28/2022
What learning algorithm is in-context learning? Investigations with linear models
Neural sequence models, especially transformers, exhibit a remarkable ca...
research
∙
11/15/2022
Hierarchical Phrase-based Sequence-to-Sequence Learning
We describe a neural transducer that maintains the flexibility of standa...
research
∙
11/02/2022
Characterizing Intrinsic Compositionality in Transformers with Tree Projections
When trained on language data, do transformers learn some arbitrary comp...
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...
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...
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...
research
∙
05/11/2022
Identifying concept libraries from language about object structure
Our understanding of the visual world goes beyond naming objects, encomp...
research
∙
04/11/2022
Correcting Robot Plans with Natural Language Feedback
When humans design cost or goal specifications for robots, they often pr...
research
∙
03/19/2022
Teachable Reinforcement Learning via Advice Distillation
Training automated agents to complete complex tasks in interactive envir...
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...
research
∙
01/30/2022
Compositionality as Lexical Symmetry
Standard deep network models lack the inductive biases needed to general...
research
∙
01/26/2022
Natural Language Descriptions of Deep Visual Features
Some neurons in deep networks specialize in recognizing highly specific ...
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...
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...
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...
research
∙
10/13/2021
Subspace Regularizers for Few-Shot Class Incremental Learning
Few-shot class incremental learning – the problem of updating a trained ...
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...
research
∙
10/04/2021
Skill Induction and Planning with Latent Language
We present a framework for learning hierarchical policies from demonstra...
research
∙
06/18/2021
Leveraging Language to Learn Program Abstractions and Search Heuristics
Inductive program synthesis, or inferring programs from examples of desi...
research
∙
06/15/2021
What Context Features Can Transformer Language Models Use?
Transformer-based language models benefit from conditioning on contexts ...
research
∙
06/07/2021
Lexicon Learning for Few-Shot Neural Sequence Modeling
Sequence-to-sequence transduction is the core problem in language proces...
research
∙
06/01/2021
Implicit Representations of Meaning in Neural Language Models
Does the effectiveness of neural language models derive entirely from ac...
research
∙
05/15/2021
The Low-Dimensional Linear Geometry of Contextualized Word Representations
Black-box probing models can reliably extract linguistic features like t...
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 ...
research
∙
04/15/2021
Multitasking Inhibits Semantic Drift
When intelligent agents communicate to accomplish shared goals, how do t...
research
∙
12/23/2020
Representing Partial Programs with Blended Abstract Semantics
Synthesizing programs from examples requires searching over a vast, comb...
research
∙
10/08/2020
Learning to Recombine and Resample Data for Compositional Generalization
Flexible neural models outperform grammar- and automaton-based counterpa...
research
∙
09/24/2020
Task-Oriented Dialogue as Dataflow Synthesis
We describe an approach to task-oriented dialogue in which dialogue stat...
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...
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...
research
∙
06/24/2020
Compositional Explanations of Neurons
We describe a procedure for explaining neurons in deep representations b...
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...
research
∙
04/21/2020
Experience Grounds Language
Successful linguistic communication relies on a shared experience of the...
research
∙
03/11/2020
A Benchmark for Systematic Generalization in Grounded Language Understanding
Human language users easily interpret expressions that describe unfamili...
research
∙
06/10/2019
A Survey of Reinforcement Learning Informed by Natural Language
To be successful in real-world tasks, Reinforcement Learning (RL) needs ...
research
∙
04/21/2019
Good-Enough Compositional Data Augmentation
We propose a simple data augmentation protocol aimed at providing a comp...
research
∙
04/02/2019
Pragmatically Informative Text Generation
We improve the informativeness of models for conditional text generation...
research
∙
02/19/2019