Papers by Eamon Duede
Confabulation: The Surprising Value of Large Language Model Hallucinations (2024.acl-long)
Copied to clipboard
| Challenge: | 'confabulations' are inherently problematic and AI research should eliminate this flaw, but confabulation is not a problem. |
| Approach: | They argue that measurable semantic characteristics of large language model (LLM) hallucinations mirror a human propensity to utilize increased narrativity as a cognitive resource for sense-making and communication. |
| Outcome: | The proposed study shows that measurable semantic characteristics of LLM confabulations mirror human propensity to utilize increased narrativity as a cognitive resource for sense-making and communication. |
The Diminishing Returns of Masked Language Models to Science (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that masked language models can improve downstream tasks by pretraining larger models for longer on more data. |
| Approach: | They empirically evaluate the extent to which these results extend to tasks in science by using 14 domain-specific transformer-based masked language models. |
| Outcome: | The proposed model can improve on 12 scientific tasks, but not all. |