Patrick Lewis Profile
Patrick Lewis

@PSH_Lewis

Followers
5K
Following
2K
Media
21
Statuses
349

London-based AI/NLP Research Scientist. I lead RAG, Tool-use and Agents at Cohere. Previous Fundamental AI Research at Meta AI, FAIR, UCL AI

London, England
Joined August 2018
Don't wanna be here? Send us removal request.
@_kire_kara_
Erik Arakelyan
1 year
👋Psst! Want more faithful, verifiable and robust #LLM reasoning than with CoT, but using external solvers is meh? Our FLARE💫uses Logic Programming with Exhaustive Simulated Search to achieve this.🧵 With @PMinervini @PSH_Lewis @pat_verga @IAugenstein https://t.co/cSHn97iLVJ
3
10
33
@PSH_Lewis
Patrick Lewis
1 year
😅
@nickfrosst
Nick Frosst
1 year
So happy to see @sarahookr and @PSH_Lewis on the AI 100 :) they have both contributed so much to @cohere and the field in general. Working with such impactful and ingenious people is one of the best perks of being at cohere :)
13
1
119
@s_hofstaetter
Sebastian Hofstätter
1 year
@karpathy @Ouponatime38 We build this at cohere 🙌 - claim level citations throughout our whole annotation, training, and inference stack.
@s_hofstaetter
Sebastian Hofstätter
2 years
Command-R by Cohere is OUT NOW! Download it at your favorite model store 🎉 It’s been quite a ride to get to this point and I’m incredibly proud of what we have achieved with RAG, tool use, and all of Cohere. I want to highlight one particular unique aspect of ⌘-R: citations!
2
6
51
@osanseviero
Omar Sanseviero
1 year
@Teknium1 Command R+ is great for tool usage. We added tools (web search, url fetching, document parsing, image generation, CosXL for editing, etc). We even added a calculator before the ipad
0
2
16
@mervenoyann
merve
1 year
document AI landed to @huggingface chat, powered by open-source models (@cohere Command-R+) with tool calling 🛠️✨ explore many tools including image generation, image editing and more at Hugging Chat 🤗💬
5
24
168
@mattzcarey
Matt Carey
2 years
feels @cohere model slaps :)
5
7
50
@seraphinagt
Seraphina Goldfarb-Tarrant @ ACL 🇦🇹
2 years
New paper! RAG-timely: *MultiContrievers: Analysis of Dense Retrieval Representations* w/ @PSH_Lewis @EntilZhaPR @JaneDwivedi https://t.co/dUjWrm2NQ5. Months late after the ArXiv upload 😅 because we were too busy at @cohere releasing multiple new LLMs 🔥. TLDR & details in 🧵
Tweet card summary image
arxiv.org
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream...
1
14
48
@natolambert
Nathan Lambert
2 years
Evaluation in AI has only works when a problem space is sufficiently scoped. We no longer evaluate LLMs on specific things, we use them for almost all our digital thinking. There is really no solution to all our eval wishes.
1
6
42
@soldni
Luca Soldaini 🎀
2 years
maybe controversial, but: Prompts are a property of models, not benchmarks. Assuming the opposite leads to benchmark hacking. Corollary: LLM devs gotta start releasing their prompts when model drops!
@kipperrii
kipply
2 years
@percyliang all models will favour some sort of prompt, and the reason you get lower scores is that people report with the prompt that makes sense for their models. optimally elicited performance (sans chain-of-thought or k-shot shenanigans) is actually much fairer.
2
4
43
@PSH_Lewis
Patrick Lewis
2 years
New paper from our team, led by @pat_verga Are you: * Doing evaluation with LLMs? * Using a huge model? * Worried about self-recognition? Try an ensemble of smaller LLMs. Use a PoLL: less biased, faster, 7x cheaper. Works great on QA & Arena-hard evals https://t.co/Lhvx5GN8I8
9
38
183
@victormustar
Victor M
2 years
Command R+ is underrated for everyday use 👀. The speed & the balance of good reasoning, concise answers, and nice writing style makes it perhaps the best daily assistant 🔥
8
11
62
@_valsai
Vals AI
2 years
Just updated our benchmark to include the new Cohere Command models and DBRX! See results at
1
2
12
@aidangomez
Aidan Gomez
2 years
Introducing Rerank 3! Our latest model focused on powering much more complex and accurate search. It's the fastest, cheapest, and highest performance reranker that exists. We're really excited to see how this model influences RAG applications and search stacks.
21
120
717
@arena
lmarena.ai
2 years
Exciting news - the latest Arena result are out! @cohere's Command R+ has climbed to the 6th spot, matching GPT-4-0314 level by 13K+ human votes! It's undoubtedly the **best** open model on the leaderboard now🔥 Big congrats to @cohere's incredible work & valuable contribution
42
295
1K
@NandoDF
Nando de Freitas
2 years
I’m a huge fan of LLM efforts that emphasise multilingualism because they make AI far more inclusive and accessible. Congratulations @cohere
@aidangomez
Aidan Gomez
2 years
Multilinguality is something that is crucial for equitable utility of this technology. We want our models to work for as many people, organizations, and markets as possible. We perform strongly across 10 languages and we're eager to expand this further.
4
12
72
@LangChainAI
LangChain
2 years
👂 @cohere Integration Package 🦜 Hot off the heels of Cohere's v5 sdk supporting tool calling and their new Command R+ model, we're excited to announce the `langchain-cohere` package, which exposes all of their integrations ranging from their chat models to model-specific
7
53
201
@W4ngatang
Alex Wang
2 years
This drove me crazy for a while: We had internal experiments showing RM > LLM for evaluation, which felt really counterintuitive to me. Nice to get external confirmation, and thanks for building the benchmark @natolambert ! :)
@natolambert
Nathan Lambert
2 years
Thx to @cohere's SOTA reward model, LLM-as-a-judge isn't SOTA on RewardBench :)
1
7
63
@jordnb
Jordan Burgess
2 years
Cohere's Chat interface with new ⌘R+ model looks... really good! 📄 search + cite 💻 web browsing 🐍 python Watch this https://t.co/3uJkFSKKjK
4
17
129
@cohere
cohere
2 years
More exciting news, our latest Command R and R+ models are now accessible via @awscloud SageMaker! This further builds on our collaboration and allows enterprises to start deploying our RAG-optimized models at production scale. Try our new models on SageMaker today.
5
31
147
@itsSandraKublik
Sandra Kublik
2 years
mind-blow by how good ⌘ R+ multi-step tool use is 🤯 rewrites my sloppy query -> fetches numbers -> plots them with citations
5
25
161