
📄 Paper: arxiv.org/abs/2610.17724 🧑💻 Code: github.com/rsanayei/Sauron Grateful for the collaboration this summer at @ScaleAILabs with @RazvanDuu @mhrezaeics @Haaris_Riaz @robert_nlp @Yminglai @liuying04 @msurd @danielyuez

working on #nlproc at University of Arizona

📄 Paper: arxiv.org/abs/2610.17724 🧑💻 Code: github.com/rsanayei/Sauron Grateful for the collaboration this summer at @ScaleAILabs with @RazvanDuu @mhrezaeics @Haaris_Riaz @robert_nlp @Yminglai @liuying04 @msurd @danielyuez

Our paper accepted at EMNLP 2026 main conference! 🎉 @emnlpmeeting "The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction" 👉 arxiv.org/abs/2510.06198 🌟 Highlight: an efficient, self-derived reward that supervises RE reasoning content, no LLM-as-a-judge needed! 📌 We propose (1) CogRE, a cognitively-inspired reasoning framework; and (2) Hit@Dict, a reward built from the model's own correct explanations ✨Thanks @msurd for the guidance and support!

The Department of Computer Science at the University of Arizona (@uarizona) has 2 open faculty positions: One in all areas & all ranks, and one Associate/Full professor working in AI who will also serve as Director of UA’s Cognitive Science program. See jobs.cs.arizona.edu.

A great essay about the issues with using gen AI in education: seewhatuthink.com/field-guid…

TL;DR Our results indicate that the age of (text-only) pre-training may not be over. Raw text holds more signal than tokens alone — syntax trees are just one structure we can model explicitly. Work done w/ Hyungji Kim & @msurd. End🧵. Blogpost: hriaz17.github.io/SiPE/ Paper: arxiv.org/abs/2608.06111

Positional embeddings discard syntax, keeping only order & distance. We show that syntax can be reintroduced by adding two lightweight tag embeddings, looked up from small tables, into the model's input embedding, resulting in improved fundamental language modeling. Delighted that our paper on Syntax-informed Positional Embeddings (SiPE) was accepted to EMNLP 2026 main conference! 🥂 w/ Hyungji Kim & @msurd #EMNLP2026 #InductiveBias #PreTraining
Positional embeddings encode order and distance, but are agnostic to syntax. "Please move this large file to another folder." To act, move must bind file (object) and folder (destination). Absolute PE: no link. Relative PE/RoPE: "six tokens apart." A dependency parse tree: one arc. Introducing Syntax-informed Positional Embeddings (SiPE) (1/n)🧵

The Computer Science Department at U.Arizona is looking to hire multiple tenure-track and multiple teaching faculty this year. If you are searching for a faculty position and like sunshine, consider applying! ☀️🌵 cs.arizona.edu/currently-ope…



Co-authors: @Yminglai @Vikas_NLP_UA @msurd — thank you! See you in Suzhou, Nov 4–9. 🙏 #EMNLP2025 (6/6)

Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/s…

An important new EMNLP paper coming from our lab, with several nice and cool co-authors :)
Our paper accepted at EMNLP 2025 Main! 🎉 @emnlpmeeting “How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark” 👉 arxiv.org/abs/2505.18761 📌 We introduce GSM-DC: a controlled benchmark for reasoning under Irrelevant Context (IC). We systematically vary reasoning depth and IC level via a knowledge DAG to study LLM reasoning behavior under distractions, not just accuracy🧭 👥 Huge thanks to my awesome team: @_ethan_huang @LiangZhang4825 @msurd @WilliamWangNLP @PanLiangming

This is actually a really solid context engineering template. Kudos, @AnthropicAI

This is a good idea: 2025.emnlp.org/desk-rejectio…

Today (4/25, 11am EST)! In our final CS Colloquium of this series, @msurd shares how combining symbolic rules with neural models leads to more explainable information extraction. #NLP #ExplainableAI @KCSciences_UML @uarizona see details👉 ow.ly/fZL250BGU4M

I am truly humbled to receive this award. It represents everything I stand for. I consider it the apex of my career.