Picture for Kanishk Gandhi

Kanishk Gandhi

Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels

Add code
Apr 22, 2024
Viaarxiv icon

Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models

Add code
Apr 17, 2024
Viaarxiv icon

Stream of Search (SoS): Learning to Search in Language

Add code
Apr 01, 2024
Viaarxiv icon

Social Contract AI: Aligning AI Assistants with Implicit Group Norms

Add code
Oct 26, 2023
Viaarxiv icon

Exciton-Polariton Condensates: A Fourier Neural Operator Approach

Add code
Sep 27, 2023
Figure 1 for Exciton-Polariton Condensates: A Fourier Neural Operator Approach
Figure 2 for Exciton-Polariton Condensates: A Fourier Neural Operator Approach
Figure 3 for Exciton-Polariton Condensates: A Fourier Neural Operator Approach
Figure 4 for Exciton-Polariton Condensates: A Fourier Neural Operator Approach
Viaarxiv icon

Understanding Social Reasoning in Language Models with Language Models

Add code
Jun 21, 2023
Figure 1 for Understanding Social Reasoning in Language Models with Language Models
Figure 2 for Understanding Social Reasoning in Language Models with Language Models
Figure 3 for Understanding Social Reasoning in Language Models with Language Models
Figure 4 for Understanding Social Reasoning in Language Models with Language Models
Viaarxiv icon

Certified Reasoning with Language Models

Add code
Jun 06, 2023
Figure 1 for Certified Reasoning with Language Models
Figure 2 for Certified Reasoning with Language Models
Figure 3 for Certified Reasoning with Language Models
Figure 4 for Certified Reasoning with Language Models
Viaarxiv icon

Strategic Reasoning with Language Models

Add code
May 30, 2023
Figure 1 for Strategic Reasoning with Language Models
Figure 2 for Strategic Reasoning with Language Models
Figure 3 for Strategic Reasoning with Language Models
Figure 4 for Strategic Reasoning with Language Models
Viaarxiv icon

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning

Add code
Oct 14, 2022
Figure 1 for Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Figure 2 for Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Figure 3 for Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Figure 4 for Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Viaarxiv icon

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

Add code
Feb 23, 2021
Figure 1 for Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
Figure 2 for Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
Figure 3 for Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
Figure 4 for Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
Viaarxiv icon