🚨 Reverse Thinking Makes LLMs Stronger Reasoners
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
02.12.2024 19:29 — 👍 19 🔁 11 💬 1 📌 2
The default feed needs to be significantly improved so that user don't have to customize. This will increase user retention @bsky.app
25.11.2024 02:11 — 👍 4 🔁 0 💬 0 📌 0
+1
25.11.2024 01:21 — 👍 0 🔁 0 💬 0 📌 0
Nice to see the LLM research community here.
Let's see if this can stand the test of time.
22.11.2024 17:12 — 👍 3 🔁 0 💬 0 📌 0
Thanks Abhilasha!
20.11.2024 06:10 — 👍 1 🔁 0 💬 0 📌 0
I see a lot of irrelevant posts in my timeline. Recommendation algorithm needs to change probably?
20.11.2024 05:58 — 👍 2 🔁 0 💬 1 📌 0
My first post here.
Had a great trip to MIT.
17.11.2024 18:12 — 👍 4 🔁 0 💬 0 📌 0
Hi Everyone! This is my first post.
AI people: Say 'Hi'!
17.11.2024 07:36 — 👍 2 🔁 0 💬 0 📌 0
PhD student at UC Berkeley. NLP for signed languages and LLM interpretability. kayoyin.github.io
🏂🎹🚵♀️🥋
assistant professor in computer science / data science at NYU. studying natural language processing and machine learning.
Interested in cognition and artificial intelligence. Research Scientist at Google DeepMind. Previously cognitive science at Stanford. Posts are mine.
lampinen.github.io
Research Scientist @ Google Deepmind. Opinions are my own.
minsukchang.com
Staff Research Scientist at Google DeepMind. ML for Biology and Chemistry (Previously NLP). Former adjunct assistant prof at NYU.
All opinions my own.
https://scholar.google.com/citations?user=bRpjhycAAAAJ&hl=en&oi=ao
AI policy researcher, wife guy in training, fan of cute animals and sci-fi. Started a Substack recently: https://milesbrundage.substack.com/
Co-founder & Chief Scientist at Yutori. Prev: Senior Director leading FAIR Embodied AI at Meta, and Professor at Georgia Tech.
Research Scientist @allen_ai & Affiliate Assistant Prof @UW; Researching on LLM alignment, eval, synthetic data, reasoning, agent. Ex: Google, Meta FAIR;
Research Scientist NLP @ Google DeepMind
https://norakassner.github.io/
Postdoc at UW NLP 🏔️. #NLProc, computational social science, cultural analytics, responsible AI. she/her. Previously at Berkeley, Ai2, MSR, Stanford. Incoming assistant prof at Wisconsin CS. https://lucy3.github.io
Research Scientist at Meta • ex Cohere, Google DeepMind • https://www.ruder.io/
Professor at UW; Researcher at Meta. LMs, NLP, ML. PNW life.
Researching reasoning at OpenAI | Co-created Libratus/Pluribus superhuman poker AIs, CICERO Diplomacy AI, and OpenAI o-series / 🍓
Head of Responsible AI, CTO Office, Bloomberg.
I lead Cohere For AI. Formerly Research
Google Brain. ML Efficiency, LLMs,
@trustworthy_ml.
Associate professor at CMU, studying natural language processing and machine learning. Co-founder All Hands AI
Visiting Scientist at Schmidt Sciences. Visiting Researcher at Stanford NLP Group
Interested in AI safety and interpretability
Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
