What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length

Lindia Tjuatja(Carnegie Mellon University), Sophie Hao(New York University), Graham Neubig(Carnegie Mellon University), Tal Linzen(New York University)
arXiv (Cornell University)
November 4, 2024
10.48550/arxiv.2411.02528
Cited by 0

Related Papers

Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
|ACM Computing Surveys|2022|3.5k
Language Models of Code are Few-Shot Commonsense Learners
|Unknown|2022|106
PAL: Program-aided Language Models
|arXiv (Cornell University)|2022|104
CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code
|Unknown|2023|79
Do LLMs Exhibit Human-like Response Biases? A Case Study in Survey Design
|Transactions of the Association for Computational Linguistics|2024|61