Papers by Peter Brusilovsky
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation (2024.acl-long)
Copied to clipboard
| Challenge: | generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are paraphrased and then used to fine-tune downstream models. |
| Approach: | They propose to use taboo words, hints by previous outlier solutions, and chaining on previous outliest solutions to augment text datasets as part of instructions to LLMs augmenting text dataset. |
| Outcome: | The proposed methods increase diversity of generated texts, but performance is highest with hints. |
Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems (2026.findings-acl)
Copied to clipboard
Zhangqi Duan, Nigel Fernandez, Arun Balajiee Lekshmi Narayanan, Mohammad Hassany, Rafaella Sampaio de Alencar, Peter Brusilovsky, Bita Akram, Andrew Lan
| Challenge: | Existing solutions to automate KC generation and tagging for open-ended programming problems are highly labor-intensive and prone to bias and errors. |
| Approach: | They propose an automated pipeline for KC generation and tagging for open-ended programming problems using large language models. |
| Outcome: | The proposed method outperforms existing ones and outperfies human-written KCs on future student response prediction. |
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | generative large language models are increasingly used for data augmentation tasks . text samples are mostly selected randomly and a comprehensive overview of other sample selection strategies is lacking. |
| Approach: | They compare random sample selection strategies and random sample sampling strategies to evaluate their effects in a low-resource setting. |
| Outcome: | The proposed model performance improvements are compared with other sample selection strategies. |
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness (2023.emnlp-main)
Copied to clipboard
| Challenge: | generative large language models (LLMs) are replacing human workers for some tasks . crowdsourcing has several downsides: 1) the workforce is costly, 2) output quality is difficult to achieve, and 3) there are overheads related to the design and organization of the process. |
| Approach: | They investigate whether ChatGPT-created paraphrases are more diverse and robust . they use a crowdsourcing tool to collect training or validation examples . |
| Outcome: | The proposed models are more diverse and robust than the existing models. |
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for keyphrase generation do not provide a desideratum for the number of keyphrases in texts. |
| Approach: | They propose a recurrent generative model that generates multiple keyphrases as delimiter-separated sequences. |
| Outcome: | The proposed model outperforms baseline models on all datasets. |
LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have compared LLM-based augmentations with established methods, but the results are contradictory. |
| Approach: | They compare the performance of LLM-based augmentation methods with established ones . they found that LLMs are worthy of deployment only when very small number of seeds is used . |
| Outcome: | The proposed methods are worthy of deployment only when very small number of seeds is used. |