When training dense models on large collections, what strategies give OOD retrieval? Resource-intensive methods like data augmentation & pretraining help.. But what about the training strategy itself 🤔 In our work, we show 3️⃣ ingredients 🧑‍🍳 for a great retrieval recipe 🍝

🤕 Have you ever wondered if LMs generate responses based on your provided input context? 🤨 How can I ensure that LM is giving me a response based on my context? We introduce Strict Grounding along with dataset, metric to evaluate whether LM truly grounds to input context.

🤔How could you evaluate whether your Vision Language Model (VLM) is closely reaching the capabilities of GPT-4V? We’re excited to present 🔥Prometheus-Vision, the first open-source VLM specialized for evaluating other VLMs based on fine-grained scoring criteria, with co-lead

❗New multilingual paper❗ 🤔LMs good at reasoning are mostly English-centric (MetaMath, Orca 2, etc). 😃Let’s adapt them to solve multilingual tasks. BUT without using multilingual data! We present LangBridge, a zero-shot approach to adapt LMs for multilingual reasoning.

🤔 Do we always need a human preference for effective LLM alignment after an SFT stage? Our answer is NO 🙅‍♂️ We present a ✨preference-free alignment approach✨, leveraging an off-the-shelf retriever with effective regularizer functions: Regularized Relevance Reward (R^3). [1/n]

New preprint "Semiparametric Token-Sequence Co-Supervision" We introduce semiparametric token-sequence co-supervision, which trains LM by simultaneously leveraging supervision from a parametric token and a nonparametric sequence embedding space. arxiv.org/abs/2403.09024

📢 Excited to share that we will organize the 3rd workshop on Knowledge-Augmented NLP at ACL 2024. We will have six amazing speakers! We welcome your submissions and invite you to discuss with our speakers and organizers at the workshop. Looking forward to seeing you in Thailand!

🚨 New LLM Reasoning Paper 🚨 Q. How can LLMs self-improve their reasoning ability? ⇒ Introducing Self-Explore⛰️🧭, a training method specifically designed to help LLMs avoid reasoning pits by learning from their own outputs! [1/N]

Announcing our latest addition to the OLMo family, OLMo 1.7!🎉Our team's efforts to improve data quality, training procedures and model architecture have led to a leap in performance. See how OLMo 1.7 stacks up against its peers and peek into the technical details on the blog:

🚀 We're excited to share the technical report of Pegasus-1, our 17B-parameter VLM, setting new benchmarks in video understanding. It surpasses larger models like Gemini Pro and Ultra in video conversation, QA, summarization, and temporal understanding. bit.ly/pegasus-1-tech…

#NLProc Introducing 🔥Prometheus 2, an open-source LM specialized on evaluating other language models. ✅Supports both direct assessment & pairwise ranking. ✅ Improved evaluation capabilities compared to its predecessor. ✅Can assess based on user-defined evaluation criteria.

🚨 New LLM personalization/alignment paper 🚨 🤔 How can we obtain personalizable LLMs without explicitly re-training reward models/LLMs for each user? ✔ We introduce a new zero-shot alignment method to control LLM responses via the system message 🚀

🤔How can we systematically assess an LM's proficiency in a specific capability without using summary measures like helpfulness or simple proxy tasks like multiple-choice QA? Introducing the ✨BiGGen Bench, a benchmark that directly evaluates nine core capabilities of LMs.

🚨 New paper 🚨 How Large Language Models Acquire Factual Knowledge During Pretraining? I’m thrilled to announce the release of my new paper! 🎉 This research explores how LLMs acquire and retain factual knowledge during pretraining. Here are some key insights:

🤔 Humans excel at generalizing planning into extrapolated data or rapidly adapting with limited train data. How is it possible for language models? Introducing 🧠Cognitive Map for Language Models, a framework achieving Optimal Planning via Verbally Representing the World Model🌍

We are hosting wonderful NLP colleagues at KAIST on their way to ACL Bangkok! 🤩 On-site registration is closed, but the talks will be broadcast on Zoom. Please join us! Date/Time: Aug 10, 2024, 10:05-12:30 KST (UCT+9) Parallel Session 1: Advanced Language Models and AI