ReNeuIR at SIGIR 2024: The Third Workshop on Reaching Efficiency in Neural Information Retrieval
Bibliographic record
Abstract
The Information Retrieval (IR) community has a rich history of empirically measuring novel retrieval methods in terms of effectiveness and efficiency. However, as the search ecosystem is developing rapidly, comparatively little attention has been paid to evaluating efficiency in recent years, which raises the question of the cost-benefit ratio between effectiveness and efficiency. In this regard, it has become difficult to compare and contrast systems in an empirically fair way. Factors including hardware configurations, software versioning, experimental settings, and measurement methods all contribute to the difficulty of meaningfully comparing search systems, especially where efficiency is a key component of the evaluation. Furthermore, efficiency is no longer limited to time and space but has found new, challenging dimensions that stretch to resource, sample, and energy efficiency and have implications for users, researchers, and the environment. Examining algorithms and models through the lens of efficiency and its trade-off with effectiveness requires revisiting and establishing new standards and principles, from defining relevant concepts, to designing measures, to creating guidelines for making sense of the significance of findings. The third iteration of ReNeuIR aims to bring the community together to debate these questions and collaboratively test and improve a benchmarking framework for efficiency derived from the discussions of the first two iterations of this workshop. We provide a first prototype of this framework by organizing a shared task track focused on comparability and reproducibility at the workshop.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".