Hailey Joren

I was raised in a community that emphasized integrity and joined Anthropic because I wanted to ensure this critical moment in AI goes well for humanity. I’m grateful to work somewhere that chose not to sacrifice principles for any amount of revenue, even amid enormous pressure.

@megan_richards_ thank you @megan_richards_ !

@HaileyJoren huge congratulations Hailey! This is awesome, and what a beautiful photo to celebrate your journey!

PhD in Computer Science, University of California San Diego 🎓 My research focused on uncertainty and safety in AI systems, including 🤷‍♀️letting models say "I don't know" under uncertainty 🔎understanding and reducing hallucinations 🔁 methods for answering "how much will providing data X improve performance on Y?" at inference time Many thanks to my advisor @berkustun, to my incredible research collaborators, and to my wonderful friends, husband and family. Getting a PhD while becoming a first-time parent is definitely a recipe for growth!

🚨New blog post out! It's really well written with great graphics 😉😎 About sufficient context in #LLMs for #RAG, based on the project from our amazing intern @HaileyJoren !

Come see our poster # 230 tomorrow in the morning session at #ICLR2025 ✨Sufficient Context: a new lens on RAG systems✨ w/ @HaileyJoren, @DaChengJuan1, Jianyi Zhang, @ankurtaly , Chun-Sung Ferng Paper: arxiv.org/abs/2411.06037 Project page: github.com/hljoren/suffic…

I couldn't make it to ICLR this year but co-author @CyrusRashtchian will be around to chat! 📄 Paper (ICLR ’25): arxiv.org/abs/2411.06037 💻 Key Findings & Prompts: github.com/hljoren/suffic… #RAG #ICLR2025

Our work suggests that solving RAG hallucination problems requires moving beyond just improving retrieval—we need models that can accurately determine when retrieved information suffices for answering and abstain when appropriate confidence thresholds aren't met.

When RAG systems hallucinate, is the LLM misusing available information or is the retrieved context insufficient? In our #ICLR2025 paper, we introduce "sufficient context" to disentangle these failure modes. Work w J. Zhang, C.S. Ferng, @DaChengJuan1, @ankurtaly @CyrusRashtchian

@PeterWestTM @UBC_CS @CAIDA_UBC @ChrisGPotts @StanfordHAI @stanfordnlp Wonderful news, congratulations!!

I'm very excited to be starting my dream job as faculty at @UBC_CS @CAIDA_UBC in 2025 and postdoc-ing with @ChrisGPotts at @StanfordHAI @stanfordnlp this year! I am recruiting students this cycle who are curious to explore the mysteries and limitations of LMs / GenAI ...

Baby’s first ICLR! (And mine too!) He had plenty of constructive feedback for mom’s poster pitch

And that’s a wrap! If you made it this far, check out our paper at ICLR or online. We’ll be at Halle B #227 Thu 9 May 4:30pm — 6:30pm CEST PDF: haileyjoren.github.io/files/conceptu… ICLR: iclr.cc/virtual/2024/p…

*End-to-end models don’t have to rely on a (likely incomplete) set of concepts and can exhibit inflated performance due to spurious correlations in the input. One of the benefits of predicting with concepts is better interpretability and removing spurious correlations

✅Easy: train a model to automate a routine task ❌Hard: ensure the model is accurate with minimal human oversight In our latest #ICLR24, we introduce a modeling paradigm for this setting Joint w @CharlieTMarx @berkustun PDF:haileyjoren.github.io/files/conceptu… ICLR:iclr.cc/virtual/2024/p…