🔥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

🙋‍♀️How to present the same text in diff. tasks/domains as diff. embeddings W/O training? We introduce Instructor👨‍🏫, an instruction-finetuned embedder that can generate text embeddings tailored to any task given the task instruction➡️sota on 7⃣0⃣tasks👇! instructor-embedding.github.io

Language models (LMs) are already deployed in many real-world applications and used to interact with users 👩‍🦰, but these models are primarily evaluated non-interactively. How can we evaluate LMs interactively and why is it important? (1/8)

Introducing Demonstrate–Search–Predict (𝗗𝗦𝗣), a framework for composing search and LMs w/ up to 120% gains over GPT-3.5. No more prompt engineering.❌ Describe a high-level strategy as imperative code and let 𝗗𝗦𝗣 deal with prompts and queries.🧵 arxiv.org/abs/2212.14024

The #cs224n poster session is happening now! We are super excited about amazing, cutting-edge NLP posters from ~650 students!

And here at the #cs224n #NLProc with Deep Learning poster session at Tressider (Stanford University) is almost all of the (large!) teaching team.

Prompting is cool and all, but isn't it a waste of compute to encode a prompt over and over again? We learn to compress prompts up to 26x by using "gist tokens", saving memory+storage and speeding up LM inference: arxiv.org/abs/2304.08467 (w/ Xiang Lisa Li and noahdgoodman) 🧵

New from Google DeepMind: When can you trust your LLM? We show that LLMs consistently overestimate their own accuracy on some topics (eg nutrition) while underestimating it on others (eg math). Our Few-shot Recalibrator fixes LLM over/under-confidence: arxiv.org/abs/2403.18286 🧵

Introducing *Transfusion* - a unified approach for training models that can generate both text and images. arxiv.org/pdf/2408.11039 Transfusion combines language modeling (next token prediction) with diffusion to train a single transformer over mixed-modality sequences. This

Eliciting Language Model Behaviors with Investigator Agents We train AI agents to help us understand the space of language model behaviors, discovering new jailbreaks and automatically surfacing a diverse set of hallucinations. Full report: transluce.org/automated-elic…

Can we get language models to exhibit certain behaviors? We train investigator models to elicit target behaviors from LMs, which helps us proactively detect harmful responses and hallucination!

This year, I have 4 exceptional students on the academic job market, and they couldn’t be more diffferent, with research spanning AI policy, robotics, NLP, and HCI. Here’s a brief summary of their research, along with one representative work each:

Lisa Li (Xiang Lisa Li) changes how people fine-tune (prefix tuning, the original PEFT), generate (diffusion LM, non-autoregressively), improve (GV consistency fine-tuning without supervision), and evaluate language models (using LMs). Prefix tuning: arxiv.org/abs/2101.00190

I’m hiring PhD students in computer science at Columbia! Our lab will tackle core challenges in understanding and controlling neural models that interact with language. for example, - methods for LLM control - discoveries of LLM properties - pretraining for understanding

When Xiang Lisa Li built diffusion LMs in 2022 (arxiv.org/abs/2205.14217), we were interested in more powerful controllable generation (inference-time conditioning on an arbitrary reward), but inference was slow. Interestingly, the main advantage now is speed. Impressive to see

What would truly open-source AI look like? Not just open weights, open code/data, but *open development*, where the entire research and development process is public *and* anyone can contribute. We built Marin, an open lab, to fulfill this vision: