Parameter Lab

‼️ New paper from Parameter Lab! ⛓️‍💥 We identify privacy collapse, a silent failure mode of LLMs: LLMs fine-tuned on seemingly benign data can lose their ability to respect contextual privacy norms. Done by @anmgoel during his internship! Check-out 👇

🧪 Our latest research: Does SEO boost the visibility of content in LLM-based conversational search? We present C-SEO Bench, a benchmark to evaluate conversational SEO strategies. Key takeaway: SEO methods that target LLM do not work. But surprisingly, traditional SEO is not dead: it still matters, as LLMs tend to favour content already ranked higher in their input.

🎉 Very excited to see our new Leaky Thoughts 🫗 paper featured among last week's top AI papers by both @dair_ai and @TheAITimeline! - teapaw.org/dair_ai/status/1936825… - teapaw.org/TheAITimeline/status/1… ➡️ Learn more about the paper in this great thread by @omarsar0: teapaw.org/omarsar0/status/193571… ➡️ ArXiv link: arxiv.org/abs/2506.15674

👥 We're Hiring: Senior/Junior Data Engineer! 📍 Remote or Local | Full-Time or Part-Time At ResearchTrend.AI, we’re building a platform that connects researchers and AI engineers worldwide—helping them stay ahead with daily digests, insightful summaries, and interactive events. Our LLM-powered ecosystem also bridges the gap between cutting-edge research and industry leaders. If you're passionate about data, AI, and making an impact, we’d love to have you on board! What You’ll Do: ✔ Build Scalable Data Pipelines – Design and optimize workflows using tools like Airflow. ✔ Work Closely with AI Experts & Engineers – Collaborate to solve real-world data challenges. ✔ Optimize and Maintain Systems – Keep our data infrastructure fast, secure, and adaptable. What You Bring: ✅ Proficiency in Airflow & PostgreSQL – You know your way around complex workflows and databases. ✅ Strong Python Skills – Clean, efficient, and maintainable code is your thing. ✅ (Bonus) Experience with LLMs – A huge plus as we integrate AI-driven solutions. ✅ Problem-Solving Mindset – You enjoy tackling challenges with real impact. ✅ Team Spirit – Excellent collaboration and communication. Why Join Us? 🚀 Make a Difference – Your work directly enhances how research is shared and discovered. 🌍 Flexibility – Choose full-time or part-time, work remotely or locally. ⚡ Innovative Environment – AI, research, and data-driven solutions all in one place. 🤝 Great Team – Work with passionate, talented people shaping the future of research. Ready to Join? Send your resume + a short note on why you’re a great fit to [email protected]. Be part of a team that’s redefining research with AI! #Hiring #DataEngineer #AI #RemoteJobs

🚨📄 Exciting new research! Discover when and at what scale we can detect if specific data was used in training LLMs — a method known as Membership Inference (MIA)! Our findings open new doors for using MIA as potential legal evidence in AI. More info in the 🧵below.

📢 Parameter Lab is at the #ACL2024 conference in Bangkok! Come to see our two posters: - TRAP 🪤 about black-box LLM fingerprinting: Tuesday 13 Aug 12:15-13:15 - Apricot 🍑 about black-box calibrated confidence score estimation: Tuesday 13 Aug 16:00-17:30

Attending #ICML2024 and looking for a research internship in trustworthy AI for LLMs? Reach out to @coallaoh and @framart1 at the conference! teapaw.org/parameterlab/status/18…

🔎 Parameter Lab is looking for a Research Intern for roughly the period of October 2024 - February 2025. You’ll do research on trustworthy AI for LLMs or multi-modal foundational models. Your research work is expected to lead to a top-tier conference submission. Prior intern projects: - ProPILE (NeurIPS’23 spotlight): arxiv.org/abs/2307.01881 - TRAP (ACL’24 findings): arxiv.org/abs/2402.12991 - Apricot (ACL’24): arxiv.org/abs/2403.05973 We expect you to have a Master’s degree (or equivalent) in AI/ML or related fields. It is a big plus to have hands-on experience with research in the related topics, such as Trustworthy AI, Privacy and Security for AI, XAI, and LLMs. ➡️ If interested, please visit: parameterlab.de/careers

🎉📜We are thrilled to announce that we have two papers accepted at #ACL2024! 🍑Apricot to obtain calibrated confidence estimate for black-box LLMs, led by @dnnslmr teapaw.org/dnnslmr/status/1767584… 🪤 TRAP for LLM fingerprinting using adversarial prompt, led by @framart1 teapaw.org/framart1/status/179113… More details in their respective threads.

🗣️ For our Chilean audience 🇨🇱: Join Martin Gubri @framart1 , our Research Lead, at IALAB of @cen_ia this Wednesday for a talk on "Trustworthy Machine Learning in the era of Large Language Models". He'll highlight our latest research called ProPILE, TRAP, and APRICOT, tackling privacy, compliance, and uncertainty in LLMs. Discover how our work is paving the way to a future of reliable AI! #MachineLearning #TrustworthyAI #Talk