Papers by Chien-Ju Ho
From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives? (2026.findings-acl)
Copied to clipboard
| Challenge: | large language models are often used as annotators at scale, but are not faithful estimators of human perspectives. |
| Approach: | They characterize the conditions under which large language models outperform human annotators . they find they are statistically superior frontline estimators based on low variance . |
| Outcome: | The proposed model outperforms human annotators when predicting subgroup opinions on subjective tasks. |
Exploring the Cost-Effectiveness of Perspective Taking in Crowdsourcing Subjective Assessment: A Case Study of Toxicity Detection (2025.naacl-long)
Copied to clipboard
| Challenge: | toxicity evaluation tasks require annotations to accurately reflect opinions of subgroups . toxicity tasks require annotators to take the opinions of a subgroup simultaneously . |
| Approach: | They propose to use perspective taking to obtain opinions from subgroups . they propose to prompt annotators to take perspectives of contrasting subgroup simultaneously . |
| Outcome: | The proposed approach can be cost-effective and improve quality under limited budget. |