Picture for Jennifer Hu

Jennifer Hu

Language Models Fail to Introspect About Their Knowledge of Language

Add code
Mar 10, 2025
Viaarxiv icon

Re-evaluating Theory of Mind evaluation in large language models

Add code
Feb 28, 2025
Viaarxiv icon

Shades of Zero: Distinguishing Impossibility from Inconceivability

Add code
Feb 27, 2025
Viaarxiv icon

One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

Add code
Nov 07, 2024
Viaarxiv icon

Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models

Add code
May 15, 2024
Figure 1 for Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models
Figure 2 for Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models
Figure 3 for Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models
Figure 4 for Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models
Viaarxiv icon

Auxiliary task demands mask the capabilities of smaller language models

Add code
Apr 03, 2024
Viaarxiv icon

Language models align with human judgments on key grammatical constructions

Add code
Jan 19, 2024
Figure 1 for Language models align with human judgments on key grammatical constructions
Figure 2 for Language models align with human judgments on key grammatical constructions
Viaarxiv icon

Prompt-based methods may underestimate large language models' linguistic generalizations

Add code
May 22, 2023
Viaarxiv icon

Expectations over Unspoken Alternatives Predict Pragmatic Inferences

Add code
Apr 07, 2023
Viaarxiv icon

An AI Dungeon Master's Guide: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons

Add code
Dec 20, 2022
Viaarxiv icon