Pith. sign in

REVIEW 5 cited by

InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.01820 v4 pith:2Z37R66L submitted 2023-01-04 cs.IR cs.AI

Vitor Jeronymo , Luiz Bonifacio , Hugo Abonizio , Marzieh Fadaee , Roberto Lotufo , Jakub Zavrel , Rodrigo Nogueira This is my paper · ORCID
classification cs.IRcs.AI
keywords inparsinpars-v2llmsmodelsretrievalsyntheticdatadataset
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, InPars introduced a method to efficiently use large language models (LLMs) in information retrieval tasks: via few-shot examples, an LLM is induced to generate relevant queries for documents. These synthetic query-document pairs can then be used to train a retriever. However, InPars and, more recently, Promptagator, rely on proprietary LLMs such as GPT-3 and FLAN to generate such datasets. In this work we introduce InPars-v2, a dataset generator that uses open-source LLMs and existing powerful rerankers to select synthetic query-document pairs for training. A simple BM25 retrieval pipeline followed by a monoT5 reranker finetuned on InPars-v2 data achieves new state-of-the-art results on the BEIR benchmark. To allow researchers to further improve our method, we open source the code, synthetic data, and finetuned models: https://github.com/zetaalphavector/inPars/tree/master/tpu

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A new MTEB state-of-the-art for text embeddings is reported by combining multi-granularity LLM-generated hard negatives with curriculum training and an anchor-token-aware pooling method.

  2. Bridging the Gap: From Ad-hoc to Proactive Search in Conversations

    cs.IR 2025-06 conditional novelty 6.0 of 10

    Conv2Query fine-tunes an LLM to convert conversational context into ad-hoc queries, enabling off-the-shelf retrievers to work effectively on proactive search in conversations.

  3. Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization

    cs.IR 2025-05 conditional novelty 6.0 of 10

    Using direct preference optimization with reranker or GPT-3.5 preferences to align synthetic query generation improves downstream dense retrieval effectiveness on MS MARCO and TREC-DL.

  4. Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Contrastive fine-tuning often degrades strong dense retrievers, while combining cross-encoder listwise distillation with diverse synthetic queries consistently improves them.

  5. Improving Scientific Document Retrieval with Academic Concept Index

    cs.IR 2026-01 conditional novelty 4.0 of 10

    Academic concept indexes that track which concepts remain uncovered make LLM-generated training queries and document snippets more effective for scientific retrieval.

Pith tools