How can we understand neural chatbots in terms of interpretable, symbolic mechanisms? To explore this question, we constructed a Transformer that implements the classic ELIZA chatbot algorithm (with @Abhishek_034 and @danqi_chen). Paper: (1/6)

RT @PrincetonPLI: In a new blog post, @HowardYen1 and @xiye_nlp introduce HELMET and LongProc, two benchmarks from a recent effort to build….

RT @michahu8: Training on a little 🤏 formal language BEFORE natural language can make pretraining more efficient!. How and why does this wo….

RT @_awettig: 🤔 Ever wondered how prevalent some type of web content is during LM pre-training?. In our new paper, we propose WebOrganizer….

RT @parksimon0808: Does all LLM reasoning transfer to VLM? In context of Simple-to-Hard generalization we show: NO! We also give ways to re….

RT @gaotianyu1350: Introducing MeCo (metadata conditioning then cooldown), a remarkably simple method that accelerates LM pre-training by s….

RT @johnhewtt: I’m hiring PhD students in computer science at Columbia!. Our lab will tackle core challenges in understanding and controlli….

RT @xiye_nlp: 🔔 I'm recruiting multiple fully funded MSc/PhD students @UAlberta for Fall 2025! Join my lab working on NLP, especially reaso….

RT @cocosci_lab: (1/5) Very excited to announce the publication of Bayesian Models of Cognition: Reverse Engineering the Mind. More than a….

RT @RTomMcCoy: 🤖🧠 I'll be considering applications for postdocs & PhD students to start at Yale in Fall 2025!. If you are interested in the….

RT @ang3linawang: I am recruiting PhD students for Fall 2025 at Cornell Tech! If you are interested in topics relating to machine learning….

RT @amuuueller: I'm recruiting PhD students for our new lab, coming to Boston University in Fall 2025!. Our lab aims to understand, improve….

RT @Abhishek_034: Progressive distillation, where a student model learns from multiple checkpoints of the teacher, has been shown to improv….

RT @RTomMcCoy: 🤖🧠NOW OUT IN PNAS🧠🤖. Language models show many surprising behaviors. E.g., they can count 30 items more easily than 29. In E….

RT @aksh_555: 🤖 NEW PAPER 🤖. Chain-of-thought reasoning (CoT) can dramatically improve LLM performance. Q: But what *type* of reasoning do….

RT @jyangballin: We're launching SWE-bench Multimodal to eval agents' ability to solve visual GitHub issues. - 617 *brand new* tasks from 1….

RT @gaotianyu1350: Very proud to introduce two of our recent long-context works:. HELMET (best long-context benchmark imo): .

RT @gaotianyu1350: Meet ProLong, a Llama-3 based long-context chat model! (64K here, 512K coming soon). ProLong use….

RT @xiamengzhou: 🌟 Exciting update! Gemma2-9b + SimPO ranks at the top of AlpacaEval 2 (❗LC 72.4) and leads the WildBench leaderboard amon….

RT @gaotianyu1350: If you are attending ICML this year, stop by our workshop on long-context foundation models! . Schedule: https://t.co/….

@BingbinL I’ll also have a poster about this project at the ICML Mechanistic Interpretability workshop in Vienna next week ( and would love to chat there 🙂.