Topic Modeling Enhancement using Summaries Generated by LLM Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Designing effective topic models for long and unstructured documents is essential for detecting significant topics within them. However, traditional topic modeling approaches have certain drawbacks, such as the presence of overlapping topics and difficulties in processing long documents. This research investigates the potential of large language models (LLMs) to enhance the uncovering of underlying topics within these documents. This paper compares two methods of using the BERTopic model. The first method segments the documents into paragraphs and classifies them using BERTopic, and the second method involves an LLM dividing documents into token segments and summarizing them. These summaries are then classified into coherent topics using the BERTopic model. The results show that summarizing the documents and then classifying them using BERTopic yields better performance values compared to segmenting the documents into paragraphs and then classifying them using BERTopic.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it