Pith. sign in

REVIEW 4 cited by

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

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 2501.16075 v1 pith:XTCYA42E submitted 2025-01-27 cs.CL cs.AIcs.IR

Maxime Louis , Hervé Déjean , Stéphane Clinchant This is my paper · ORCID
classification cs.CLcs.AIcs.IR
keywords compressionpiscoaccuracyexistinggenerationmodelspretrainingretrieval-augmented
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated data, relying solely on sequence-level knowledge distillation from document-based questions. With the ability to fine-tune a 7-10B LLM in 48 hours on a single A100 GPU, PISCO offers a highly efficient and scalable solution. We present comprehensive experiments showing that PISCO outperforms existing compression models by 8% in accuracy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. ARC-Encoder: learning compressed text representations for large language models

    cs.CL 2025-10 conditional novelty 6.0 of 10

    ARC-Encoder pools queries in an encoder's last attention layer to produce compressed continuous representations that a frozen decoder consumes as token embeddings.

  2. MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts

    cs.AI 2025-10 conditional novelty 6.0 of 10

    MHA-RAG encodes retrieved exemplars into order-invariant soft prompts via multi-head attention, claiming ~20-point effective-accuracy gains over RAG at ~10x lower inference FLOPs.

  3. Reranking with Compressed Document Representation

    cs.IR 2025-05 conditional novelty 6.0 of 10

    A reranker trained on 8-token PISCO document embeddings plus a short query achieves near-identical nDCG@10 to full-text rerankers on BeIR and TREC-DL while running up to 16x faster.

  4. SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression

    cs.CL 2025-07 conditional novelty 5.0 of 10

    SARA combines short natural-language snippets with vector-compressed summaries of the remaining retrieved documents, improving RAG answer quality under 512/1024-token context budgets.

Pith tools