Bibliographic record
Abstract
This paper introduces a flexible and scalable methodology for abstractive summarization called K-BABS. Following the analysis of the source documents a knowledge base called a task blueprint is used to identify patterns in the representation of the source documents and generate summary text from them. This knowledge-based approach allows for implicit understanding and transformation of the source documents’ content, given that the task blueprint is carefully crafted for the summarization task and domain of interest. ABSUM is a system that implements this methodology for the guided summarization task of the Text Analysis Conferences. Knowledge for two broad news categories has been manually encoded. Evaluation shows that the abstractive summaries of ABSUM have better linguistic quality and almost twice the content density of state-of-the-art extractive summaries. When used in combination with an extractive summarizer, evaluation shows that ABSUM improves the summarizer’s coverage of the source documents by a statistically significant amount, and exceeds the content score of the state of the art in text summarization. A discussion of extensions to this work including ways to automate the knowledge acquisition procedure is included.
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.
How this classification was reachedexpand
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".