Pith Number

pith:IETDEUVI

pith:2023:IETDEUVIITI6SUJJVXN7DDVHOH

not attested not anchored not stored refs resolved

RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!

Jimmy Lin, Ronak Pradeep, Sahel Sharifymoghaddam

An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.

arxiv:2312.02724 v1 · 2023-12-05 · cs.IR

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IETDEUVIITI6SUJJVXN7DDVHOH}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model.

C2weakest assumption

That the NovelEval test set truly contains only queries and passages created after the model's training cutoff and that no leakage occurred during fine-tuning or evaluation.

C3one line summary

RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.

References

42 extracted · 42 resolved · 5 Pith anchors

[1] MS MARCO: A Human Generated MAchine Reading COmprehension Dataset 2016 · arXiv:1611.09268

[2] Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. InPars : Unsupervised dataset generation for information retrieval. In Proceedings of the 45th International ACM SIGIR Confer 2022

[3] Leonid Boytsov, Preksha Patel, Vivek Sourabh, Riddhi Nisar, Sayani Kundu, Ramya Ramanathan, and Eric Nyberg. 2023. InPars-Light : Cost-effective unsupervised training of efficient rankers. arXiv:2301. 2023

[4] Barla Cambazoglu, Hugo Zaragoza, Olivier Chapelle, Jiang Chen, Ciya Liao, Zhaohui Zheng, and Jon Degenhardt 2010

[5] Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2020. Overview of the TREC 2020 deep learning track. In Proceedings of the Twenty-Ninth Text REtrieval Conference Proceedings (TREC 2020) 2020

Cited by

24 papers in Pith

RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models

Layer-wise Token Compression for Efficient Document Reranking

SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization

Layer-wise Token Compression for Efficient Document Reranking

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

Receipt and verification

First computed	2026-05-17T23:38:49.741805Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d

Aliases

arxiv: 2312.02724 · arxiv_version: 2312.02724v1 · doi: 10.48550/arxiv.2312.02724 · pith_short_12: IETDEUVIITI6 · pith_short_16: IETDEUVIITI6SUJJ · pith_short_8: IETDEUVI

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH \
  | 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: 41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a1764aefe86bc9a17300c6cb55a7b0430df1adeed4cd013070a656f3e56ba22b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2023-12-05T12:39:00Z",
    "title_canon_sha256": "7c9305e0dd384640ff8818643ff60e7641a95c68dde202c7fa51bf54f9435d63"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2312.02724",
    "kind": "arxiv",
    "version": 1
  }
}