Papers › No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
Guilherme Moraes Rosa, Luiz Bonifacio, Vitor Jeronymo, Hugo Abonizio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira
Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications. In this work, we question this practice by showing that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that rerankers largely outperform dense ones of similar size in several tasks. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points. Finally, we confirm that in-domain effectiveness is not a good indicator of zero-shot effectiveness. Code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Biomedical Information Retrieval | BioASQ (BEIR) | monoT5-3B | nDCG@10 | 0.579 | #1 of 6 | Archive leaderboard | report |
| Biomedical Information Retrieval | NFCorpus (BEIR) | monoT5-3B | nDCG@10 | 0.383 | #1 of 7 | Archive leaderboard | report |
| Biomedical Information Retrieval | TREC-COVID (BEIR) | monoT5-3B | nDCG@10 | 0.795 | #2 of 6 | Archive leaderboard | report |
| Fact Checking | CLIMATE-FEVER (BEIR) | monoT5-3B | nDCG@10 | 0.280 | #2 of 4 | Archive leaderboard | report |
| Fact Checking | FEVER (BEIR) | monoT5-3B | nDCG@10 | 0.849 | #1 of 4 | Archive leaderboard | report |
| Fact Checking | SciFact (BEIR) | monoT5-3B | nDCG@10 | 0.777 | #1 of 5 | Archive leaderboard | report |
| Question Answering | FiQA-2018 (BEIR) | monoT5-3B | nDCG@10 | 0.513 | #1 of 4 | Archive leaderboard | report |
| Question Answering | HotpotQA (BEIR) | monoT5-3B | nDCG@10 | 0.759 | #1 of 4 | Archive leaderboard | report |
| Question Answering | NQ (BEIR) | monoT5-3B | nDCG@10 | 0.633 | #2 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections