pith. machine review for the scientific record. sign in
Pith Number

pith:5X6JLHOG

pith:2020:5X6JLHOGN2HVWSPONIMAI4JMZX
not attested not anchored not stored refs pending

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Edouard Grave, Gautier Izacard

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

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open

Claims

C1strongest claim

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.

C2weakest assumption

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.

C3one line summary

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

1 machine-checked theorem link

Cited by

19 papers in Pith

Receipt and verification
First computed2026-05-17T23:38:14.048603Z
Builderpith-number-builder-2026-05-17-v1
SignaturePith Ed25519 (pith-v1-2026-05) · public key
Schemapith-number/v1.0

Canonical hash

edfc959dc66e8f5b49ee6a1804712ccdc5c9f93fb11fcb97e071dfa1db53a4a3

Aliases

arxiv: 2007.01282 · arxiv_version: 2007.01282v2 · doi: 10.48550/arxiv.2007.01282
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
  }
}