pith:5X6JLHOG
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
Generative models for open-domain question answering gain from retrieving multiple passages and combining their evidence.
arxiv:2007.01282 v2 · 2020-07-02 · cs.CL · cs.LG
Record completeness
Claims
We obtain state-of-the-art results on the Natural Questions and TriviaQA open benchmarks. Interestingly, we observe that the performance of this method significantly improves when increasing the number of retrieved passages. This is evidence that generative models are good at aggregating and combining evidence from multiple passages.
That the observed gains are attributable to the generative model's ability to aggregate evidence across passages rather than to confounding factors such as retrieval quality, prompt formatting, or benchmark-specific artifacts; the abstract provides no controls or ablation details to isolate this mechanism.
Augmenting generative models with passage retrieval yields state-of-the-art results on Natural Questions and TriviaQA, with performance scaling positively as more passages are retrieved.
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-17T23:38:14.048603Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519 (pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
edfc959dc66e8f5b49ee6a1804712ccdc5c9f93fb11fcb97e071dfa1db53a4a3
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/5X6JLHOGN2HVWSPONIMAI4JMZX \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: edfc959dc66e8f5b49ee6a1804712ccdc5c9f93fb11fcb97e071dfa1db53a4a3
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "77e01979aac7fd9eade2a6e28fb35908563b4982a042002d099aafa2280e1925",
"cross_cats_sorted": [
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2020-07-02T17:44:57Z",
"title_canon_sha256": "701ee88276237a38762e765c99c525be5ecd6ae1b0d408730dcaaba6404913b2"
},
"schema_version": "1.0",
"source": {
"id": "2007.01282",
"kind": "arxiv",
"version": 2
}
}