AewolFlow
HomeLibraryProjectsDrafts & writing
Plans & Billing
Log in
AewolFlow
Log in
HomeLibraryProjectsDrafts & writing
Settings
←Projects

Example project

Try editing this brief. Changes stay in this tab and disappear when you leave or reload, even after saving the preview.

Start a real project↗

Example project

Retrieval or a longer context?

Keep the evidence, your decisions and the next questions in one place.

Source papers
03
Saved passages
00

Example · temporary

Example · temporary

This preview includes your current edits. Unsaved changes are included in the download, too.

Retrieval or a longer context?

Research question

For question answering over our own documents, should we start with retrieval or a longer context window?

Evidence

Your notes and interpretations. Saving a paper does not verify a claim.

A retrieval baseline is worth testing

RAG combines a generator with retrieved documents and evaluates it on knowledge-intensive tasks. That motivates a baseline, not a guarantee for our application. Source: Lewis et al., 2020 ↗

DPR studies a dual-encoder approach to passage retrieval. It is a useful reference when designing our retrieval evaluation. Source: Karpukhin et al., 2020 ↗

More context is not the whole answer

Lost in the Middle finds sensitivity to where relevant information appears in the tasks it evaluates. This does not establish the behavior of every current model. Source: Liu et al., 2023 ↗

Decisions

Proposed experiment — not yet run

  • Compare a retrieval baseline and a long-context baseline on the same questions and documents.
  • Record source support, latency, and cost separately.
  • Choose an approach only after reviewing those results.

This is an illustrative research plan, not a finding or recommendation from the paper authors.

Open questions

  • Which question types fail on our own documents?
  • Does document position affect the model we actually plan to use?
  • How will we assess whether a citation supports the answer?
  • What latency and per-question cost can we accept?

Source papers

3

Real papers for this example. Removing one changes only this preview.

  1. 01

    Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks↗

    Patrick Lewis et al. · 2020 · arXiv:2005.11401

    Example summary · paraphrased

    Studies generation with retrieved external information.

    Open reader↗
  2. 02

    Dense Passage Retrieval for Open-Domain Question Answering↗

    Vladimir Karpukhin et al. · 2020 · arXiv:2004.04906

    Example summary · paraphrased

    Studies dense passage retrieval for open-domain question answering.

    Open reader↗
  3. 03

    Lost in the Middle: How Language Models Use Long Contexts↗

    Nelson F. Liu et al. · 2023 · arXiv:2307.03172

    Example summary · paraphrased

    Evaluates how relevant information's position affects performance in long contexts.

    Open reader↗
Browse your library↗
Use with your AI↗

Optional · connect your own AI from settings.