REVIEW 8 cited by
InPars: Data Augmentation for Information Retrieval using Large Language Models
Not yet reviewed by Pith; the record is open.
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
read the original abstract
The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot transfer learning to various tasks. However, not all IR tasks and domains can benefit from one single dataset equally. Extensive research in various NLP tasks has shown that using domain-specific training data, as opposed to a general-purpose one, improves the performance of neural models. In this work, we harness the few-shot capabilities of large pretrained language models as synthetic data generators for IR tasks. We show that models finetuned solely on our unsupervised dataset outperform strong baselines such as BM25 as well as recently proposed self-supervised dense retrieval methods. Furthermore, retrievers finetuned on both supervised and our synthetic data achieve better zero-shot transfer than models finetuned only on supervised data. Code, models, and data are available at https://github.com/zetaalphavector/inpars .
Forward citations
Cited by 8 Pith papers
-
Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders
Bekko a8m, with 7.7M active parameters, scores 56.2 on MMTEB Multilingual v2 Retrieval, beating mE5 models and BGE-M3, while a25m reaches 57.5, on par with gte-multilingual-base.
-
How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
On a new benchmark of post-April 2025 queries, LLM rerankers show a 5-15% performance drop compared with familiar benchmarks, and lightweight models match them on efficiency and sometimes accuracy.
-
SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads
A gated hybrid retrieval system shows rule-based keywords beat LLM queries for retargeting but lose for prospecting, and routing 10% of users to LLM semantic search raises ad conversions by 27.6%.
-
Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings
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.
-
Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization
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.
-
RaDeR: Reasoning-aware Dense Retrieval Models
A math-trained dense retriever and reranker, built from MCTS reasoning trajectories and self-reflection, outperforms strong baselines on reasoning-intensive retrieval benchmarks and beats BM25 on chain-of-thought queries.
-
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
Using a fine-tuned 3B LLM to generate millions of textual relevance labels for App Store search improves the ranker's behavioral/textual Pareto frontier and lifts conversion by 0.24%.
-
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
Contrastive fine-tuning often degrades strong dense retrievers, while combining cross-encoder listwise distillation with diverse synthetic queries consistently improves them.
Discussion (0). Continue with ORCID to comment.