research
∙
09/01/2023
NeuroSurgeon: A Toolkit for Subnetwork Analysis
Despite recent advances in the field of explainability, much remains unk...
share
research
∙
05/25/2023
Language Models Implement Simple Word2Vec-style Vector Arithmetic
A primary criticism towards language models (LMs) is their inscrutabilit...
research
∙
05/24/2023
Testing Causal Models of Word Meaning in GPT-3 and -4
Large Language Models (LLMs) have driven extraordinary improvements in N...
research
∙
03/14/2023
Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs
Training data attribution (TDA) methods offer to trace a model's predict...
research
∙
03/08/2023
Comparing Trajectory and Vision Modalities for Verb Representation
Three-dimensional trajectories, or the 3D position and rotation of objec...
research
∙
01/26/2023
Break It Down: Evidence for Structural Compositionality in Neural Networks
Many tasks can be described as compositions over subroutines. Though mod...
research
∙
01/17/2023
Are Language Models Worse than Humans at Following Prompts? It's Complicated
Prompts have been the center of progress in advancing language models' z...
research
∙
12/20/2022
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
Large-scale models combining text and images have made incredible progre...
research
∙
11/26/2022
Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex
AlphaZero, an approach to reinforcement learning that couples neural net...
research
∙
09/30/2022
Linearly Mapping from Image to Text Space
The extent to which text-only language models (LMs) learn to represent t...
research
∙
07/05/2022
Pretraining on Interactions for Learning Grounded Affordance Representations
Lexical semantics and cognitive science point to affordances (i.e. the a...
research
∙
06/23/2022
Do Trajectories Encode Verb Meaning?
Distributional models learn representations of words from text, but are ...
research
∙
03/31/2022
Do Vision-Language Pretrained Models Learn Primitive Concepts?
Vision-language pretrained models have achieved impressive performance o...
research
∙
11/10/2021
A Novel Corpus of Discourse Structure in Humans and Computers
We present a novel corpus of 445 human- and computer-generated documents...
research
∙
09/21/2021
Does Vision-and-Language Pretraining Improve Lexical Grounding?
Linguistic representations derived from text alone have been criticized ...
research
∙
09/14/2021
Frequency Effects on Syntactic Rule Learning in Transformers
Pre-trained language models perform well on a variety of linguistic task...
research
∙
09/13/2021
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Pretrained language models have been shown to encode relational informat...
research
∙
09/02/2021
Do Prompt-Based Models Really Understand the Meaning of their Prompts?
Recently, a boom of papers have shown extraordinary progress in few-shot...
research
∙
06/30/2021
The MultiBERTs: BERT Reproductions for Robustness Analysis
Experiments with pretrained models such as BERT are often based on a sin...
research
∙
01/02/2021
Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
Many Question-Answering (QA) datasets contain unanswerable questions, bu...
research
∙
12/04/2020
Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments
We present a system that enables robots to interpret spatial language as...
research
∙
10/28/2020
A Visuospatial Dataset for Naturalistic Verb Learning
We introduce a new dataset for training and evaluating grounded language...
research
∙
10/12/2020
Measuring and Reducing Gendered Correlations in Pre-trained Models
Pre-trained models have revolutionized natural language understanding. H...
research
∙
10/10/2020
Self-play for Data Efficient Language Acquisition
When communicating, people behave consistently across conversational rol...
research
∙
10/06/2020
Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
In politics, neologisms are frequently invented for partisan objectives....
research
∙
06/23/2020
Robot Object Retrieval with Contextual Natural Language Queries
Natural language object retrieval is a highly useful yet challenging tas...
research
∙
04/30/2020
When does data augmentation help generalization in NLP?
Neural models often exploit superficial ("weak") features to achieve goo...
research
∙
04/29/2020
What Happens To BERT Embeddings During Fine-tuning?
While there has been much recent work studying how linguistic informatio...
research
∙
05/28/2019
Planning with State Abstractions for Non-Markovian Task Specifications
Often times, we specify tasks for a robot using temporal language that c...
research
∙
05/15/2019
What do you learn from context? Probing for sentence structure in contextualized word representations
Contextualized representation models such as ELMo (Peters et al., 2018a)...
research
∙
05/15/2019
BERT Rediscovers the Classical NLP Pipeline
Pre-trained text encoders have rapidly advanced the state of the art on ...
research
∙
04/25/2019
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
We introduce a set of nine challenge tasks that test for the understandi...
research
∙
02/04/2019
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
Machine learning systems can often achieve high performance on a test se...
research
∙
12/28/2018
Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Work on the problem of contextualized word representation -- the develop...
research
∙
08/28/2018
WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
We release a corpus of 43 million atomic edits across 8 languages. These...
research
∙
04/23/2018