Guy Bar-Shalom

@GuyBarSh

PhD student @TechnionLive Trying to better understand LLMs Ex Research Intern @Verily | Ex Research Intern @Meta Working with @HaggaiMaron and @el_yaniv

Israel

Pinned
Guy Bar-Shalom
@GuyBarSh
Apr 15
New blogpost out 📃 "Detecting LLM Misbehaviors from the Inside Out with Deep Learning on Structured Data" (ffabffrasca.substack.com/p/detecting-ll…) [1/8]
2
Guy Bar-Shalom
@GuyBarSh
Feb 19
Check out our new ICLR 2026 paper - we explore hallucination detection through graph learning. Take a look!
Fabrizio Frasca
@ffabffrasca
Feb 18
🧵"Neural Message Passing on Attention Graphs for Hallucination Detection" at #ICLR2026 ! 🕸️We apply GNNs on the structured data LLMs produce as they generate text (e.g. attentions) to predict their errors. 📄 arxiv.org/abs/2509.24770 🤝 @GuyBarSh (co-1st) @YftahZ @HaggaiMaron
Guy Bar-Shalom
@GuyBarSh
Feb 2
Happy to share my new #ICLR2026 papers !
3
Guy Bar-Shalom
@GuyBarSh
Oct 4, 2025
[1/7] New paper: "Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT" #NeurIPS2025 [arxiv.org/pdf/2510.00296] Joint work with: @ffabffrasca (co-first), @yaniv_galron, @YftahZ , @HaggaiMaron
1
Guy Bar-Shalom
@GuyBarSh
Apr 26, 2025
📢 Introducing: Learning on LLM Output Signatures for Gray-box LLM Behavior Analysis [arxiv.org/pdf/2503.14043] A joint work with @ffabffrasca (co-first author) and our amazing collaborators: @dereklim_lzh @yoav_gelberg @YftahZ @el_yaniv @GalChechik @HaggaiMaron 🧵Thread
1