Learning to Adaptively Rank Document Retrieval System Configurations
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
Modern Information Retrieval (IR) systems have become more and more complex, involving a large number of parameters. For example, a system may choose from a set of possible retrieval models (BM25, language model, etc.), or various query expansion parameters, whose values greatly influence the overall retrieval effectiveness. Traditionally, these parameters are set at a system level based on training queries, and the same parameters are then used for different queries. We observe that it may not be easy to set all these parameters separately, since they can be dependent. In addition, a global setting for all queries may not best fit all individual queries with different characteristics. The parameters should be set according to these characteristics. In this article, we propose a novel approach to tackle this problem by dealing with the entire system configurations (i.e., a set of parameters representing an IR system behaviour) instead of selecting a single parameter at a time. The selection of the best configuration is cast as a problem of ranking different possible configurations given a query. We apply learning-to-rank approaches for this task. We exploit both the query features and the system configuration features in the learning-to-rank method so that the selection of configuration is query dependent. The experiments we conducted on four TREC ad hoc collections show that this approach can significantly outperform the traditional method to tune system configuration globally (i.e., grid search) and leads to higher effectiveness than the top performing systems of the TREC tracks. We also perform an ablation analysis on the impact of different features on the model learning capability and show that query expansion features are among the most important for adaptive systems.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.006 |
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