Pith. sign in

REVIEW 6 cited by

How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval

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

arxiv 2302.07452 v1 pith:7EZAARD7 submitted 2023-02-15 cs.IR cs.CL

classification cs.IRcs.CL
keywords augmentationretrievaldensediversegeneralizablesupervisedzero-shotachieve
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however, often suffer from effectiveness tradeoffs between supervised and zero-shot retrieval, which some argue was due to the limited model capacity. We contradict this hypothesis and show that a generalizable DR can be trained to achieve high accuracy in both supervised and zero-shot retrieval without increasing model size. In particular, we systematically examine the contrastive learning of DRs, under the framework of Data Augmentation (DA). Our study shows that common DA practices such as query augmentation with generative models and pseudo-relevance label creation using a cross-encoder, are often inefficient and sub-optimal. We hence propose a new DA approach with diverse queries and sources of supervision to progressively train a generalizable DR. As a result, DRAGON, our dense retriever trained with diverse augmentation, is the first BERT-base-sized DR to achieve state-of-the-art effectiveness in both supervised and zero-shot evaluations and even competes with models using more complex late interaction (ColBERTv2 and SPLADE++).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Mutual Linearity in and out of Stationarity for Markov Jump Processes: A Trajectory-Based Approach

    cond-mat.stat-mech 2026-04 unverdicted novelty 7.0 of 10

    Trajectory-level linear response yields mutual linearity of observables under single-edge rate perturbation for Markov jump processes, including non-stationary state and counting observables.

  2. KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.

  3. Graph World Model

    cs.LG 2025-07 reject novelty 6.0 of 10

    The Graph World Model uses action nodes and graph message passing to unify multimodal and graph-structured tasks, but its 'outperforms or matches' claim is contradicted by results on Goodreads.

  4. FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A new library, FedRAG, provides centralized and federated fine-tuning for RAG systems, with a lightweight experiment showing a RALT-based accuracy gain on MMLU global facts.

  5. FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation

    cs.CL 2025-06 conditional novelty 5.0 of 10

    FlexRAG is a modular, open-source RAG framework with text, multimodal, and web retrieval, plus evaluation tools and efficient memory-mapped indexing.

  6. A Multi-Task Evaluation of LLMs' Processing of Academic Text Input

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    The abstract reports Gemini underperforms on four academic text tasks, but the attached full text is an unrelated biomedical retrieval paper, leaving the claims unverifiable.

Pith tools