Picture for Leonie Weissweiler

Leonie Weissweiler

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

Add code
Mar 26, 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

Derivational Morphology Reveals Analogical Generalization in Large Language Models

Add code
Nov 12, 2024
Figure 1 for Derivational Morphology Reveals Analogical Generalization in Large Language Models
Figure 2 for Derivational Morphology Reveals Analogical Generalization in Large Language Models
Figure 3 for Derivational Morphology Reveals Analogical Generalization in Large Language Models
Figure 4 for Derivational Morphology Reveals Analogical Generalization in Large Language Models
Viaarxiv icon

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

Add code
Sep 25, 2024
Viaarxiv icon

SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists

Add code
Aug 30, 2024
Viaarxiv icon

UCxn: Typologically Informed Annotation of Constructions Atop Universal Dependencies

Add code
Mar 26, 2024
Viaarxiv icon

Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs

Add code
Mar 26, 2024
Figure 1 for Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs
Figure 2 for Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs
Figure 3 for Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs
Figure 4 for Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs
Viaarxiv icon

Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons

Add code
Mar 26, 2024
Figure 1 for Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
Figure 2 for Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
Figure 3 for Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
Figure 4 for Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons
Viaarxiv icon

Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena

Add code
Mar 11, 2024
Figure 1 for Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
Figure 2 for Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
Figure 3 for Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
Figure 4 for Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
Viaarxiv icon