TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Is there an LLM for condensing and surfacing recent research?

6 点作者 timlod超过 1 年前
I&#x27;ve been using ChatGPT for a while now, and find it (among other things) great to get a pointer at some seminal papers (usually older) which to seed my search with.<p>Something I yearn for is a way to quickly learn about recent advances in some more niche topics I&#x27;m not already too familiar with, mostly to quickly advance&#x2F;curb some ideas. I feel like it should be possible to make an LLM aware of (via online fine-tuning or perhaps summarized context of articles which match via some other method) new papers on Arxiv or at least abstracts collected at journals. Essentially something that, given a prompt asking for recent advances in a certain field, spits out papers that may be useful to check, ideally with a quick summary relating to the prompt (could go beyond the abstract, pulling out an idea from the main body).<p>Right now my workflow for this problem is mostly finding some sort of seed paper, and juggling abstracts on something like connectedpapers.<p>Does anyone know what the state of the art for this is, and whether something useful already exists or is being worked on in the space?

2 条评论

sargstuff超过 1 年前
<a href="https:&#x2F;&#x2F;cobusgreyling.medium.com&#x2F;implement-custom-search-in-gpt-3-5bd42e0bfc65" rel="nofollow noreferrer">https:&#x2F;&#x2F;cobusgreyling.medium.com&#x2F;implement-custom-search-in-...</a><p><a href="https:&#x2F;&#x2F;blog.rfox.eu&#x2F;en&#x2F;Programming&#x2F;How_to_run_your_own_LLM_GPT.html" rel="nofollow noreferrer">https:&#x2F;&#x2F;blog.rfox.eu&#x2F;en&#x2F;Programming&#x2F;How_to_run_your_own_LLM_...</a><p><a href="https:&#x2F;&#x2F;stackoverflow.com&#x2F;questions&#x2F;30904755&#x2F;extract-abstract-full-text-from-scientific-literature-given-doi-or-title" rel="nofollow noreferrer">https:&#x2F;&#x2F;stackoverflow.com&#x2F;questions&#x2F;30904755&#x2F;extract-abstrac...</a><p><a href="https:&#x2F;&#x2F;generativeai.pub&#x2F;what-the-heck-are-agents-10b2a995420" rel="nofollow noreferrer">https:&#x2F;&#x2F;generativeai.pub&#x2F;what-the-heck-are-agents-10b2a99542...</a><p><a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;2023&#x2F;Aug&#x2F;27&#x2F;wordcamp-llms&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;simonwillison.net&#x2F;2023&#x2F;Aug&#x2F;27&#x2F;wordcamp-llms&#x2F;</a>
weallfeelit超过 1 年前
Chris Olah&#x27;s Distill intended to do this: &quot;a new open science journal and ecosystem supporting human understanding of machine learning. Distill is an independent organization, dedicated to fostering a new segment of the research community.&quot; The journal went to sleep in 2021, unfortunately. (<a href="https:&#x2F;&#x2F;blog.research.google&#x2F;2017&#x2F;03&#x2F;distill-supporting-clarity-in-machine.html" rel="nofollow noreferrer">https:&#x2F;&#x2F;blog.research.google&#x2F;2017&#x2F;03&#x2F;distill-supporting-clar...</a>)