Picture for Kyle Mahowald

Kyle Mahowald

Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models

Add code
Mar 26, 2025
Viaarxiv icon

Language Models Fail to Introspect About Their Knowledge of Language

Add code
Mar 10, 2025
Viaarxiv icon

Constructions are Revealed in Word Distributions

Add code
Mar 08, 2025
Viaarxiv icon

Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs

Add code
Feb 18, 2025
Viaarxiv icon

How Linguistics Learned to Stop Worrying and Love the Language Models

Add code
Jan 28, 2025
Figure 1 for How Linguistics Learned to Stop Worrying and Love the Language Models
Figure 2 for How Linguistics Learned to Stop Worrying and Love the Language Models
Figure 3 for How Linguistics Learned to Stop Worrying and Love the Language Models
Figure 4 for How Linguistics Learned to Stop Worrying and Love the Language Models
Viaarxiv icon

Models Can and Should Embrace the Communicative Nature of Human-Generated Math

Add code
Sep 25, 2024
Viaarxiv icon

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Add code
Sep 18, 2024
Figure 1 for To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Figure 2 for To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Figure 3 for To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Figure 4 for To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Viaarxiv icon

Do they mean 'us'? Interpreting Referring Expressions in Intergroup Bias

Add code
Jun 25, 2024
Viaarxiv icon

Participle-Prepended Nominals Have Lower Entropy Than Nominals Appended After the Participle

Add code
May 16, 2024
Viaarxiv icon

Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs

Add code
Mar 28, 2024
Viaarxiv icon