Picture for Robert West

Robert West

There and Back Again: The AI Alignment Paradox

May 31, 2024
Viaarxiv icon

Fleet of Agents: Coordinated Problem Solving with Large Language Models using Genetic Particle Filtering

May 07, 2024
Viaarxiv icon

Edisum: Summarizing and Explaining Wikipedia Edits at Scale

Add code
Apr 04, 2024
Viaarxiv icon

Can Language Models Recognize Convincing Arguments?

Mar 31, 2024
Viaarxiv icon

The Era of Semantic Decoding

Add code
Mar 21, 2024
Figure 1 for The Era of Semantic Decoding
Figure 2 for The Era of Semantic Decoding
Figure 3 for The Era of Semantic Decoding
Viaarxiv icon

Emojinize: Enriching Any Text with Emoji Translations

Mar 07, 2024
Figure 1 for Emojinize: Enriching Any Text with Emoji Translations
Figure 2 for Emojinize: Enriching Any Text with Emoji Translations
Figure 3 for Emojinize: Enriching Any Text with Emoji Translations
Figure 4 for Emojinize: Enriching Any Text with Emoji Translations
Viaarxiv icon

Do Llamas Work in English? On the Latent Language of Multilingual Transformers

Add code
Feb 24, 2024
Viaarxiv icon

Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

Add code
Feb 23, 2024
Figure 1 for Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Figure 2 for Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Figure 3 for Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Figure 4 for Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Viaarxiv icon

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Add code
Feb 23, 2024
Figure 1 for Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
Figure 2 for Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
Figure 3 for Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
Figure 4 for Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
Viaarxiv icon

Symbolic Autoencoding for Self-Supervised Sequence Learning

Feb 16, 2024
Viaarxiv icon