Papers by Julian Nyarko
Identifying Emerging Concepts in Large Corpora (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for text analysis are not specifically designed for identifying emergent concepts, instead applying general-purpose techniques that do not account for distinct temporal patterns associated with conceptual emergence. |
| Approach: | They propose a method to identify emerging concepts in large text corpora by analyzing changes in the heatmaps of the underlying embedding space. |
| Outcome: | The proposed method outperforms existing methods by analyzing speeches in the U.S. Senate from 1941 to 2015. |
Not Your Typical Government Tipline: LLM-Assisted Routing of Environmental Protection Agency Citizen Tips (2025.emnlp-main)
Copied to clipboard
| Challenge: | Regulatory agencies often operate with limited resources and rely on tips to identify violations . but processing these tips at scale presents significant operational challenges . a case study shows advances in large language models can be utilized to support overburdened agencies . |
| Approach: | They analyze thousands of citizen tips from the EPA's "Report a Violation" system to develop an LLM-assisted pipeline for tip routing. |
| Outcome: | The proposed approach filters out 80.5% of irrelevant tips and increases overall routing accuracy from 31.8% to 82.4% compared to the current system. |