跳过导航
We used RL to train models that create curated context from long documents for downstream use by…
0:00 / 0:24

We used RL to train models that create curated context from long documents for downstream use by…

Applied Compute

@appliedcompute8346 位关注者

在 X 上查看
135 个赞下载原帖

37,368 次观看

We used RL to train models that create curated context from long documents for downstream use by agents. The models sometimes learn to invent their own abbreviations and shorthand. Optimizing with RL for downstream use produces very different artifacts from ordinary summaries: shorter, denser, creatively concise. We call these neural cheat-sheets.

8 条评论

评论来自 X (Twitter) 上的原帖

  • Applied Compute 的头像

    @appliedcompute

    Neural cheat-sheets approach the performance of learned KV-caches — which are several orders of magnitude larger and not human-readable — while preserving the auditability of natural language summaries that enterprise workflows require. One can think of a neural-cheat sheet as a learned cache in token space.

    17 个赞

  • Applied Compute 的头像

    @appliedcompute

    At deployment time, the trained model takes in a new knowledge artifact: an enterprise SOP, a meeting transcript, a coding agent trace, or even a novella, and outputs a dense set of notes that captures fine-grained detail and amortizes reasoning. This approach is used to build memory for agents, instantiated at Applied Compute as a ContextBase.

    11 个赞

  • Applied Compute 的头像

    @appliedcompute

    Read the full research report on our blog:

    15 个赞

  • Rohan Rao 的头像

    @themathgeek13

    Aligns with extraction of domain-specific ontologies and schemas from unstructured text documents, something for which we fine-tuned (with SFT/LoRA) specialized triplet extraction models for finance, chip design, legal and healthcare a couple of years ago!

    3 个赞

  • Uzay 的头像

    @uzpg_

    nice - @KaivuHariharan @atticuswzf cool to see someone do this

    3 个赞

  • Jake 的头像

    @jake_010202

    this should also be used for compaction

    1 个赞

  • legalprimes 的头像

    @LegalPrimes

    Neat

    1 个赞

  • Sebastian Buzdugan 的头像

    @sebuzdugan

    watched shorthand help agents until one abbreviation collision poisoned the next retrieval step