Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.17946 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915506779324416 |
|---|---|
| author | Zhong, Mian Wang, Pristina Field, Anjalie |
| author_facet | Zhong, Mian Wang, Pristina Field, Anjalie |
| contents | Despite numerous applications for fine-grained corpus analysis, researchers continue to rely on manual labeling, which does not scale, or statistical tools like topic modeling, which are difficult to control. We propose that LLMs have the potential to scale the nuanced analyses that researchers typically conduct manually to large text corpora. To this effect, inspired by qualitative research methods, we develop HICode, a two-part pipeline that first inductively generates labels directly from analysis data and then hierarchically clusters them to surface emergent themes. We validate this approach across three diverse datasets by measuring alignment with human-constructed themes and demonstrating its robustness through automated and human evaluations. Finally, we conduct a case study of litigation documents related to the ongoing opioid crisis in the U.S., revealing aggressive marketing strategies employed by pharmaceutical companies and demonstrating HICode's potential for facilitating nuanced analyses in large-scale data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17946 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HICode: Hierarchical Inductive Coding with LLMs Zhong, Mian Wang, Pristina Field, Anjalie Computation and Language Artificial Intelligence Human-Computer Interaction Despite numerous applications for fine-grained corpus analysis, researchers continue to rely on manual labeling, which does not scale, or statistical tools like topic modeling, which are difficult to control. We propose that LLMs have the potential to scale the nuanced analyses that researchers typically conduct manually to large text corpora. To this effect, inspired by qualitative research methods, we develop HICode, a two-part pipeline that first inductively generates labels directly from analysis data and then hierarchically clusters them to surface emergent themes. We validate this approach across three diverse datasets by measuring alignment with human-constructed themes and demonstrating its robustness through automated and human evaluations. Finally, we conduct a case study of litigation documents related to the ongoing opioid crisis in the U.S., revealing aggressive marketing strategies employed by pharmaceutical companies and demonstrating HICode's potential for facilitating nuanced analyses in large-scale data. |
| title | HICode: Hierarchical Inductive Coding with LLMs |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.17946 |