Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
Bibliographic record
Abstract
Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced from various data sources.However, we find that certain datasets can negatively impact model effectiveness -pruning 8 out of 15 datasets from the BGE collection, reduces the training set size by 2.35×, surprisingly increases nDCG@10 on BEIR by 1.0 point.This motivates a deeper examination of training data quality, with a particular focus on "false negatives", where relevant passages are incorrectly labeled as irrelevant.We utilize LLMs as a simple, cost-effective approach to identify and relabel false negatives in training datasets.Experimental results show that relabeling false negatives as true positives improves both E5 (base) and Qwen2.5-7Bretrieval models by 0.7-1.4 points on BEIR and by 1.7-1.8 points at nDCG@10 on zero-shot AIR-BENCH evaluation.Similar gains are observed for rerankers fine-tuned on the relabeled data, such as Qwen2.5-3B on BEIR.The reliability of LLMs to identify false negatives is supported by human annotation results.Our training dataset and code are publicly available.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.069 | 0.375 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.008 | 0.015 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".