Picture for Chandra Bhagavatula

Chandra Bhagavatula

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation

Add code
Dec 10, 2023
Viaarxiv icon

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Add code
Dec 04, 2023
Viaarxiv icon

"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation

Add code
Oct 26, 2023
Figure 1 for "You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation
Figure 2 for "You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation
Figure 3 for "You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation
Figure 4 for "You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation
Viaarxiv icon

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

Add code
Oct 12, 2023
Viaarxiv icon

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

Add code
Sep 02, 2023
Viaarxiv icon

Faith and Fate: Limits of Transformers on Compositionality

Add code
Jun 01, 2023
Figure 1 for Faith and Fate: Limits of Transformers on Compositionality
Figure 2 for Faith and Fate: Limits of Transformers on Compositionality
Figure 3 for Faith and Fate: Limits of Transformers on Compositionality
Figure 4 for Faith and Fate: Limits of Transformers on Compositionality
Viaarxiv icon

PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning

Add code
May 31, 2023
Figure 1 for PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Figure 2 for PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Figure 3 for PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Figure 4 for PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
Viaarxiv icon

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Add code
May 27, 2023
Viaarxiv icon

Reinforced Clarification Question Generation with Defeasibility Rewards for Disambiguating Social and Moral Situations

Add code
Dec 20, 2022
Viaarxiv icon

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

Add code
Dec 19, 2022
Viaarxiv icon