🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Introducing OpenWebMath, a massive dataset containing every math document found on the internet - with equations in LaTeX format! 🤗 Download on @HuggingFace: huggingface.co/datasets/open-… 📝 Read the paper: arxiv.org/abs/2310.06786 w/ Marco Dos Santos, Zhangir Azerbayev, Jimmy Ba!

🎉 Excited to introduce DistillSpec! Accelerate your LLM inference using Speculative Decoding with a more aligned draft model, consistently delivering a remarkable 10-45% performance uplift over standard Speculative Decoding. ✨ Combining Distilled Target with Distilled Draft,

What constitutes a good #eval metric? We bridge #MeasurementTheory in #EducationalTesting and #Psychometrics to #NLProc. We propose #MetricEval, a theory-driven framework to conceptualize and operationalize measurement error sources to evaluate #NLG metrics. #EMNLP2023 🧵

RLHF typically assumes that all training feedback comes from a single teacher, but teachers can disagree up to 37% of the time in practice. In our new paper, we introduce active teacher selection to learn from different teachers. (1/n)

When given context about a “green square” and a “blue circle”, how do language models bind corresponding shapes and colors? Using causal experiments, we find that large enough language models learn simple structured representations for binding! A thread (1/n)

OpenAI just announced GPTs and the Assistants API for “ helping developers build agent-like experiences”, but what does that mean and how does it change how we should govern AI? Some early thoughts relating to my ongoing work 🧵:

#OpenAI’s GPTs & Assistants APIs are a blast, making it much easier to build customized agents with new tools. But are they safe to deploy? 🚨 A simple & quick test against prompt injections reveals that it is fairly easy to make GPTs delete all your files 💀

I will be at #NeurIPS2023 Dec 11-16 Shoot me an email to connect! Particularly interested in: - LM eval for long-horizon / agents - Alignment / rewards generally Will present my paper on multi-objective reward aggregation at Poster sess 6 Thurs eve (neurips.cc/virtual/2023/p…)

Our team at MSR Montréal is looking for interns! Subjects range from efficient modular adaptation to building complex systems by stacking LLMs. Consider applying here : aka.ms/AAo5t0x

ToolEmu has been accepted at #ICLR2024 as a Spotlight presentation🔥 Explore our LLM-based emulation framework for identifying LLM agent risks at scale! 🎯 Demo: demo.toolemu.com 📄 Paper: arxiv.org/abs/2309.15817 🔗 Code: github.com/ryoungj/ToolEmu 🧵⬇️

Here's what I see as a likely AGI trajectory over the next decade. I claim that later parts of the path present the biggest alignment risks/challenges. The alignment world has been focusing a lot on the lower left corner lately, which I'm worried is somewhat of a Maginot line.

We are presenting ToolEmu at #ICLR2024 tomorrow! ⏲️ Friday 4:30pm-6:30pm CEST 📍 Spotlight poster session, Hall B #80 I won't be able to attend ICLR this year but don't miss the chance to meet our amazing collaborators!

🔍 Current LLM evaluations fall short: • Lack nuanced understanding of model capabilities • Overly focused on quantitative metrics • Difficult for humans to interpret Introducing LLM Report Cards! A novel approach for qualitative, interpretable model evaluation. 1/N

📝 How do you choose which language model to use? Quantitative benchmarks can be uninformative and fall prey to Goodhart's Law, and even Chatbot Arena performance can be optimized for. In our new preprint, we propose generating qualitative report cards... 🧵

“What objective function do we want AI to optimize for? If we aggregate values from society, what weights do we use, and whose values?” Learn more about SRI Grad Affiliate Silviu Pitis's research, supported by an OpenAI Superalignment Fast Grant. 🔗 uoft.me/aWX