Alert button
Picture for Jacob Andreas

Jacob Andreas

Alert button

Linearity of Relation Decoding in Transformer Language Models

Aug 17, 2023
Evan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau

Figure 1 for Linearity of Relation Decoding in Transformer Language Models
Figure 2 for Linearity of Relation Decoding in Transformer Language Models
Figure 3 for Linearity of Relation Decoding in Transformer Language Models
Figure 4 for Linearity of Relation Decoding in Transformer Language Models
Viaarxiv icon

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Aug 01, 2023
Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim

Figure 1 for Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Figure 2 for Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Figure 3 for Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Figure 4 for Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Viaarxiv icon

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

Jun 30, 2023
Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas

Figure 1 for The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Figure 2 for The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Figure 3 for The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Figure 4 for The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Viaarxiv icon

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

Jun 23, 2023
Lionel Wong, Gabriel Grand, Alexander K. Lew, Noah D. Goodman, Vikash K. Mansinghka, Jacob Andreas, Joshua B. Tenenbaum

Figure 1 for From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Figure 2 for From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Figure 3 for From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Figure 4 for From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Viaarxiv icon

Decision-Oriented Dialogue for Human-AI Collaboration

Jun 01, 2023
Jessy Lin, Nicholas Tomlin, Jacob Andreas, Jason Eisner

Figure 1 for Decision-Oriented Dialogue for Human-AI Collaboration
Figure 2 for Decision-Oriented Dialogue for Human-AI Collaboration
Figure 3 for Decision-Oriented Dialogue for Human-AI Collaboration
Figure 4 for Decision-Oriented Dialogue for Human-AI Collaboration
Viaarxiv icon

Grokking of Hierarchical Structure in Vanilla Transformers

May 30, 2023
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning

Figure 1 for Grokking of Hierarchical Structure in Vanilla Transformers
Figure 2 for Grokking of Hierarchical Structure in Vanilla Transformers
Figure 3 for Grokking of Hierarchical Structure in Vanilla Transformers
Figure 4 for Grokking of Hierarchical Structure in Vanilla Transformers
Viaarxiv icon

Natural Language Decomposition and Interpretation of Complex Utterances

May 15, 2023
Harsh Jhamtani, Hao Fang, Patrick Xia, Eran Levy, Jacob Andreas, Ben Van Durme

Figure 1 for Natural Language Decomposition and Interpretation of Complex Utterances
Figure 2 for Natural Language Decomposition and Interpretation of Complex Utterances
Figure 3 for Natural Language Decomposition and Interpretation of Complex Utterances
Figure 4 for Natural Language Decomposition and Interpretation of Complex Utterances
Viaarxiv icon

Measuring and Manipulating Knowledge Representations in Language Models

Apr 03, 2023
Evan Hernandez, Belinda Z. Li, Jacob Andreas

Figure 1 for Measuring and Manipulating Knowledge Representations in Language Models
Figure 2 for Measuring and Manipulating Knowledge Representations in Language Models
Figure 3 for Measuring and Manipulating Knowledge Representations in Language Models
Figure 4 for Measuring and Manipulating Knowledge Representations in Language Models
Viaarxiv icon

Language Models Trained on Media Diets Can Predict Public Opinion

Mar 28, 2023
Eric Chu, Jacob Andreas, Stephen Ansolabehere, Deb Roy

Figure 1 for Language Models Trained on Media Diets Can Predict Public Opinion
Figure 2 for Language Models Trained on Media Diets Can Predict Public Opinion
Figure 3 for Language Models Trained on Media Diets Can Predict Public Opinion
Figure 4 for Language Models Trained on Media Diets Can Predict Public Opinion
Viaarxiv icon