Pith. sign in

REVIEW 5 cited by

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

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 2407.12854 v1 pith:EI4V2FMT submitted 2024-07-09 cs.CL cs.AIcs.IRcs.LG

classification cs.CLcs.AIcs.IRcs.LG
keywords datastorescalingmodeldatalanguageretrieval-basedamountlarger
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Scaling laws with respect to the amount of training data and the number of parameters allow us to predict the cost-benefit trade-offs of pretraining language models (LMs) in different configurations. In this paper, we consider another dimension of scaling: the amount of data available at inference time. Specifically, we find that increasing the size of the datastore used by a retrieval-based LM monotonically improves language modeling and several downstream tasks without obvious saturation, such that a smaller model augmented with a large datastore outperforms a larger LM-only model on knowledge-intensive tasks. By plotting compute-optimal scaling curves with varied datastore, model, and pretraining data sizes, we show that using larger datastores can significantly improve model performance for the same training compute budget. We carry out our study by constructing a 1.4 trillion-token datastore named MassiveDS, which is the largest and the most diverse open-sourced datastore for retrieval-based LMs to date, and designing an efficient pipeline for studying datastore scaling in a computationally accessible manner. Finally, we analyze the effect of improving the retriever, datastore quality filtering, and other design choices on our observed scaling trends. Overall, our results show that datastore size should be considered as an integral part of LM efficiency and performance trade-offs. To facilitate future research, we open-source our datastore and code at https://github.com/RulinShao/retrieval-scaling.

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. Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A sparse cross-modal routing system matches or exceeds dense retrieval-augmented baselines on five KI-MMQA benchmarks at 3.4–6.8× lower FLOPs.

  2. RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects

    cs.CL 2025-01 conditional novelty 6.0 of 10

    Fine-tuning an LLM with defect detection and utility extraction tasks makes it more robust to noisy, irrelevant, and counterfactual documents in retrieval-augmented generation.

  3. Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

    cs.CL 2026-07 conditional novelty 5.0 of 10

    Hybrid RAG over UK public health guidance sharply raises MCQA accuracy and free-form faithfulness, letting smaller open models match larger closed models without retrieval.

  4. Uncovering Scaling Laws for Large Language Models via Inverse Problems

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Proposes using inverse problems to discover LLM scaling laws, but provides no empirical evidence or new results.

  5. VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction

    cs.SE 2025-04 reject novelty 4.0 of 10

    A jointly trained embedding and generation model for Verilog debugging that retrieves candidate buggy lines and types before generating fixes, reported at 64.7% Acc@1 on a new synthetic dataset.

Pith tools