NG

。

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[酸欠少女 さユり @taltalasuka]

さユりに関するお知らせ

[Lance Martin @RLanceMartin]

RAG From Scratch

Here's a set of short (5-10 min videos) and notebooks explaining > a dozen of my favorite RAG papers. Took a stab at implementing each idea myself (all code open source) and grouped according to the diagram.

Repo:
https://t.co/WDN9Tsy84t
Video playlist:
https://t.co/ctSTXXWJ49
Some highlights:

Is RAG Really Dead?
How RAG might change with long context LLMs.
Video:
https://t.co/z1ntvtWFWL

Adaptive-RAG
Dynamically route queries based on complexity to different RAG approaches. Implemented in LangGraph w/ @cohere cmd-R.
Video:
https://t.co/3hKVdSQ0Zf
Code:
https://t.co/KjcqtCL0bW
Paper (@SoyeongJeong97 et al):
https://t.co/4bIO5km1jn

Corrective-RAG
Self-correct retrieval errors in-the-loop unit tests for doc relevance and fallback to web-search. I implemented in LangGraph w/ @MistralAI-7b + @ollama for running locally.
Video:
https://t.co/8T06OVnmW4
Code:
https://t.co/jATwYQuqaN
Paper (@Jiachen_Gu et al):
https://t.co/nBO5ZxWfvU

Self-RAG
Self-correct RAG errors with in-the-loop unit tests for doc relevance, answer hallucinations, and answer quality. Implemented in LangGraph w/ @MistralAI-7b + @ollama for running locally.
Code:
https://t.co/7bEwbcY9jv
Code (local):
https://t.co/BQZ2LxEHJ3
Paper (@AkariAsai et al):
https://t.co/lTIlj4rpoT

Query Routing
Various approaches for directing questions to the correct datasource (e.g., logical, semantic, etc).
Video:
https://t.co/Ffg7Dyx6jA
Code:
https://t.co/nMLCCYEOzB

Query Structuring
Use an LLM to convert from natural language-to-<DSL> where DSL is a domain specific language required to interact with a given database (SQL, Cypher, etc).
Video:
https://t.co/LQB5zVdA2R
Code:
https://t.co/nMLCCYEOzB
Blog:
https://t.co/Z5ynzlzmWK
2/ Deep dive on graphDBs (c/o @neo4j): https://t.co/4FvtlQXl7F
3/ Query structuring docs: https://t.co/ZcgucoC4jf
4/ Self-query retriever docs: https://t.co/FBZ7OlwFCp

Multi-Representation Indexing
Use an LLM to produce document summaries ("propositions") that are optimized for retrieval. Embed these summaries for similarity search, but return full documents to the LLM for generation.
Video:
https://t.co/XU44LDd3X7
Code:
https://t.co/102QR15FSb
Paper (@tomchen0 et al):
https://t.co/ltzx6n0BUy

RAPTOR
Cluster docs in the corpus and summarize similar ones recursively. Index them all together, resulting in lower-level docs and summaries that can be retrieved to answer questions that span detailed-to-higher level.
Video:
https://t.co/bzLQRRRtQk
Code:
https://t.co/SXqOLhxAgk
Paper (@parthsarthi03 et al):
https://t.co/0aSDyiU24H

ColBERT
Improve embedding granularity w/ a contextually influenced embedding for each token in the document and query.
Video:
https://t.co/JZ6VTl24kV
Code:
https://t.co/102QR15FSb
Paper (@lateinteraction & @matei_zaharia):
https://t.co/MuTGFlAerv

Multi-Query
Re-write the user question from multiple perspectives, retrieve documents for each re-written question, return the unique documents for all queries.
Video:
https://t.co/WiHg60yDC4
Code:
https://t.co/cxsjcvPO9a
Paper:
https://t.co/GCH3lgUjT0

RAG-Fusion
Re-write the user question from multiple perspectives, retrieve documents for each re-written question, and combine the ranks of multiple search result lists to produce a single, unified ranking w/ Reciprocal Rank Fusion (RRF).
Video:
https://t.co/DWlBCu2duf
Code:
https://t.co/cxsjcvPO9a
Repo (@Raudaschl):
https://t.co/zn5iZRNaYg

Decomposition
Decompose a question into a set of sub-problems / questions, which can either be solved sequentially (use the answer from first + retrieval to answer the second) or in parallel (consolidate each answer into final answer). Various works such as Least-to-Most prompting (@denny_zhou et al) and IR-CoT present ideas that be utilized.
Video:
https://t.co/VzxTWhnNoD
Code:
https://t.co/cxsjcvPO9a
Papers:
https://t.co/ZGRt9Gqid3 https://t.co/JhGK1vHwro

Step-back prompting
First prompt the LLM to ask a generic step-back question about higher-level concepts or principles, and retrieve relevant facts about them. Use this grounding to help answer the user question.
Video:
https://t.co/JOjfkghYC2
Code:
https://t.co/cxsjcvPO9a
Paper (@denny_zhou + colleges):
https://t.co/ZIc6uaNBDx

HyDE
LLM to convert questions into hypothetical documents that answer the question. Use the embedded hypothetical documents to retrieve real documents with the premise that doc-doc similarity search can produce more relevant matches.
Video:
https://t.co/Kiy2EFCRBT
Code:
https://t.co/cxsjcvPO9a
Paper:
https://t.co/wDCkSwuK3o

[NG @N__SFW__G]

@zeechn 坏了，现在不给我推工口净是键政了

[Sheena Chestnut Greitens @SheenaGreitens]

Delighted to (finally) share this new piece in @AsianSurvey on "China's Response to War in Ukraine." A short thread: (1/n)
https://t.co/Bzvv4WzHrY

[Zhengfawei 政法委 @Zhengfawei80]

We’re all still grappling with the richness of @michaelxpettis’ insights today, plus all the outstanding audience Qs, so for sure we’ll be listening back to the recording of this morning’s conversation too, available at the link below for the next 30 days: https://t.co/QkNyqbzgTr

[醋辣小黄鱼 @Qm3JKNEhbBPOEJH]

A little gift from crazy Chinese fans! @sekise10

[NG @N__SFW__G]

#prayforkyoani

[中華人民共和国駐日本国大使館 @ChnEmbassy_jp]

京都で発生した悲惨な事件で、お亡くなりになられた方のご冥福をお祈りし、負傷された皆様にお見舞いを申し上げます。

[NG @N__SFW__G]

#prayforkyoani T.T

[NG @N__SFW__G]

我大三就坐过了…

[Z @zeechn]

北京现在还有直达太原的高铁了..

[前澤友作 @yousuck2020]

ZOZOTOWN新春セールが史上最速で取扱高100億円を先ほど突破！！日頃の感謝を込め、僕個人から100名様に100万円【総額1億円のお年玉】を現金でプレゼントします。応募方法は、僕をフォローいただいた上、このツイートをRTするだけ。受付は1/7まで。当選者には僕から直接DMします！ #月に行くならお年玉

[NG @N__SFW__G]

草（両方） #役に立ちそうで立たない中国語ネット用語講座

[NG @N__SFW__G]

往东边走咯，争取去 Big Apple 找一个从 T 大去哥大的（浑水摸鱼的）交换生

[Z @zeechn]

@N__G NGGGG!! 恭喜！
到年纪了真是捉急怎么办..

[NG @N__SFW__G]

@zeechn 是啊……又是秋天又是周末日子还好（公历农历老黄历）……加上你的朋友都到了这个年纪了……

[NG @N__SFW__G]

@zeechn 附议一个

[NG @N__SFW__G]

@YojiNoda1 大丈夫、最高のライブだった！すごく感動しました！

[NG @N__SFW__G]

@zeechn 之前给 dell 工作站装上 CentOS 也是费了一番劲……务必有线网啊

[Donald J. Trump @realDonaldTrump]

On behalf of @FLOTUS Melania and I, THANK YOU for an unforgettable afternoon and evening at the Forbidden City in Beijing, President Xi and Madame Peng Liyuan. We are looking forward to rejoining you tomorrow morning! https://t.co/ma0F7SHbVU

[NG @N__SFW__G]

@Aimer_and_staff お疲れ様でした！素敵な歌声でした！

[NG @N__SFW__G]

@Sato_Kai SPの生放送はありません。ビリビリのうpが多いのBML本体の方の生放送はありますが、日本の藝人さんたちのパートはないです。（日本語は下手です、すみません）